## Motivation and Context
`Flow#locate_authorization_server` treated every failure to fetch Protected Resource Metadata as "the server publishes none"
and took the legacy 2025-03-26 path, where the MCP server's origin becomes the authorization base URL.
A request that never reached the server, or a `5xx` or `429`, says nothing about what the server publishes,
so a transient failure moved the flow to a different authorization server, discarded client information
and tokens bound to the real one on the way, and surfaced as an unrelated error, such as a failed registration at the origin,
rather than as the fetch failure itself. The comment claimed both reference SDKs behave that way, which is not so:
outside browsers the TypeScript SDK propagates network errors from discovery, and the Python SDK propagates them
and refuses the legacy path after a `5xx` or `429` from any candidate.
Discovery now keeps trying candidate URLs until one serves a JSON object and classifies the outcome once they are exhausted.
Like the Python SDK, it remembers a `5xx` or `429` from any candidate before deciding on the legacy path;
moving on to the next candidate after a network error is what the loop already did. `MetadataNotPublishedError`
(a `4xx` other than `429`, or a body that is not a JSON object) is the only failure that selects the legacy path;
`MetadataUnreachableError` (a network error, or a `5xx` or `429`, from any candidate) is raised instead.
Both subclass `AuthorizationError`, so callers rescuing that class keep working, and `MCP::Client::HTTP` still falls back from
a failed refresh to the full flow, which repeats discovery and raises the same way unless the server has recovered.
A body over the response cap is refused outright with a plain `AuthorizationError`, as it already was on the modern path.
The message lists every candidate's failure, with the URL stripped of userinfo, query and fragment and cut to a fixed length,
but otherwise spelled as requested, and with transport and parser messages bounded, as token endpoint diagnostics already are.
The default legacy endpoints for an origin whose own metadata document is absent are unchanged.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb` and `test/mcp/client/oauth/discovery_test.rb`. Against the library
before this change, discovery in the scenarios these tests set up took the legacy path instead of raising.
## Breaking Changes
When no Protected Resource Metadata candidate serves a JSON object, a request that failed to reach the server,
or returned a `5xx` or `429`, now raises instead of attempting the legacy 2025-03-26 discovery at the MCP server's origin,
and a Protected Resource Metadata body over the response cap is refused instead of triggering that fallback.
## Motivation and Context
`MCP::Client::OAuth::Flow` takes an `http_client_factory:`, but `MCP::Client::HTTP` builds
the flow itself and passes none, so an application using `oauth:` could not add middleware to
the requests the flow makes: Protected Resource Metadata and authorization server metadata discovery,
dynamic client registration, and every token request.
The block that customizes the transport's Faraday connection does not help,
because that connection is bound to the MCP server URL and carries the `headers:` meant for that server,
and the authorization server is a different origin. The TypeScript SDK hands the transport's `fetch` to `auth()`
and the Python SDK sends the provider's requests through the transport's httpx client, so both let
an application instrument these requests; this SDK did not. (#558)
Providers now take `http_client_customizer:`, a callable invoked with the Faraday connection
the flow builds for its own requests, next to the other callables a provider already holds.
It runs after the SDK's defaults (`Accept: application/json`, no redirect following) and
between two middlewares of the SDK's own: `Flow::RequestedURLStamp`, registered before the customizer is invoked,
records the URL the flow asked for on the request environment, and `Flow::RequestedOriginGuard`, registered last,
sees what the customizer's middleware did to the request after that record. A request that would leave that origin,
by following a redirect or rewriting the URL, or that arrives without the record, is refused with
`Flow::DestinationMismatchError` before it reaches the adapter. The record lives on the environment rather than
in `env.request.context`, which stays the application's to fill or replace. The error is an `ArgumentError`
rather than an `AuthorizationError` so neither discovery nor the transport's refresh fallback can absorb
a configuration mistake. The boundary resembles the one the Python SDK keeps for its own requests,
which follows a redirect only within the origin; this flow follows none itself.
`Flow.build_http_client` assembles that connection and `Flow.new(http_client_factory:)` keeps replacing it whole.
Following done inside an adapter cannot be seen by any guard, so the documentation keeps that, `Accept-Encoding`,
and `raise_error` off the list of things a customizer may add, and notes that a recording middleware sees
client credentials and tokens.
Fixes#558.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb`, `test/mcp/client/oauth/http_oauth_test.rb`,
and the three provider test files. Against the library before this change, every one of them fails,
on the unknown keyword or on the missing reader.
## Breaking Changes
None. The customizer is opt-in, and the guard cannot fire on the SDK's own middleware-free connection.
## Motivation and Context
`Flow#refresh!` reads `client_id_metadata_document_url` from the provider unconditionally, once to decide whether
a provider without stored `client_information` may still refresh and once to build the CIMD `client_id`.
Only `Provider` defines that reader: `CrossAppAccessProvider` and `ClientCredentialsProvider`
raise `NoMethodError` once a stored `refresh_token` is found. `MCP::Client::HTTP` calls `refresh!` on any `401` while
a `refresh_token` is stored, so a `jwt-bearer` client whose authorization server issued one fails with
`NoMethodError` on the first expired token instead of refreshing. The error is not an `AuthorizationError`,
so the transport does not fall back to the grant either. RFC 7521 Section 4.1 makes a refresh token unusual
for an assertion grant, not forbidden, and one in storage must not crash the client.
The flow now reads the URL through a duck-typed helper, like `authorization_flow` and `client_assertion`,
so a provider without the reader has no CIMD URL and refreshes with its stored `client_information`:
the `refresh_token` grant is sent with the stored client authentication, and no new ID-JAG assertion is obtained.
The authorization-code registration path reads the URL through the same helper.
The docs now say that a refresh token issued anyway is used on the next `401`, and that the assertion provider
is not called again on refresh.
A refresh token stored without the `issuer` the SDK records is refused for these two providers before any request:
unlike `Provider`, they have no tokens that predate the record, and a refresh asks no validator, so such a token
would be presented to whatever authorization server discovery names. The refusal is an `AuthorizationError`,
which sends the transport back through the grant, and the grant asks.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb` refresh through a `CrossAppAccessProvider` and
a `ClientCredentialsProvider` holding a `refresh_token`, asserting the `refresh_token` grant, the Basic credentials,
and that the assertion provider is not called. A transport test in `test/mcp/client/oauth/http_oauth_test.rb` sends
a `401` to a `CrossAppAccessProvider` with a stored `refresh_token` and expects the refreshed bearer token on the retry.
All three raise `NoMethodError` against the previous library.
Further tests pin the issuer stamp on the refreshed tokens, the refusal of an authorization server that did not issue them
for a `CrossAppAccessProvider`, a clean `AuthorizationError` for a provider with neither the reader
nor stored `client_information`, and registration through DCR for a provider without the reader.
A refresh token without a recorded issuer is refused for both providers before any request is sent.
## Breaking Changes
None.
## Motivation and Context
When a server publishes no Protected Resource Metadata, discovery takes the legacy 2025-03-26 path and `prm` is `nil`.
The authorization-code branch of `run!` allowed for that by passing `prm || {}` to `resolve_scope`,
but `run_client_credentials!` and `run_jwt_bearer!` passed `prm` as is, and `resolve_scope` then
called `prm["scopes_supported"]` on `nil`. Without a non-empty challenge scope, a `ClientCredentialsProvider` or
`CrossAppAccessProvider` pointed at such a server therefore failed with `NoMethodError` after discovery and before
the token request or the ID-JAG callback, instead of running its grant against the legacy authorization base
the way `Provider` does.
`resolve_scope` now treats a missing PRM as advertising no scopes, so the challenge scope or the provider's own scope applies,
and the authorization-code branch passes `prm` unchanged like the other two.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb` run the `client_credentials` grant against a PRM-less server with metadata
at the origin, checking the provider's scope, the `resource`, and the recorded issuer, and run the `jwt-bearer` grant against
a server without any metadata, checking the default token endpoint, the assertion audience, the `resource`, and the recorded
issuer. Both raise `NoMethodError` against the previous library.
## Breaking Changes
None.
## Motivation and Context
On the legacy 2025-03-26 path, taken when a server publishes no Protected Resource Metadata,
the authorization server metadata is fetched from the MCP server's origin, which that spec names
as the authorization base URL, but its `issuer` was never compared with that origin.
RFC 8414 Section 3.3 requires the comparison, the 2025-03-26 spec makes RFC 8414 a MUST for clients,
and the TypeScript and Python SDKs both compare on this path, tolerating only a trailing slash.
The flow nevertheless used the unverified `issuer` as the authorization server's identity everywhere:
tokens were stamped with it, stored client information was matched against it, the `private_key_jwt`
and ID-JAG assertions took it as their audience, and `authorization_request_validator` was shown it.
A server on that path could therefore claim any issuer. Claiming the one that minted the stored tokens made
`refresh!` send the refresh token and the stored client secret to the server's own token endpoint, claiming
the one that issued stored client information made the flow reuse those credentials there, and a validator
allow-listing the claimed issuer approved the request.
The legacy path now applies the same check as the modern one: the document's `issuer` must be the origin,
rendered with or without a trailing slash, and any other document is refused before registration, redirect,
or token request. A server without a metadata document still gets the spec's default endpoints.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb` serve legacy metadata at the MCP server origin that claims
`https://auth.example.com` and check that the flow, a refresh of tokens issued by that server,
and a flow holding client information bound to it are all refused before any request, with the validator never asked
and the credentials never presented. Metadata naming the origin, with or without a trailing slash and with
endpoints under a path prefix, completes the flow, including the RFC 9207 `iss` check. The former test
of a path-prefix issuer now expects the refusal. The refusal tests fail against the previous library.
## Breaking Changes
A server without Protected Resource Metadata whose authorization server metadata names an issuer other than
its origin is refused instead of used. The TypeScript and Python SDKs already refuse such a server,
and the 2025-03-26 spec places the metadata at the origin.
## Motivation and Context
`ClientCredentialsProvider` builds a fixed `client_credentials` token request: `grant_type`, `scope`,
`resource`, and the client authentication that `Flow#post_to_token_endpoint` adds. An authorization server
that requires further parameters, such as Auth0's `audience`, cannot be used through `oauth:` at all,
and giving up `oauth:` also gives up the bearer header and the 401-driven retry that the transport provides.
RFC 6749 Section 8.2 allows extension parameters on the token request, and the TypeScript SDK lets
a provider shape its token request through `prepareTokenRequest`. `ClientCredentialsProvider.new` now takes
`token_request_params:`, a Hash of String keys and values added to every token request the provider makes,
and `Flow#post_to_token_endpoint` reads the same name by duck typing, so a `Provider` or `CrossAppAccessProvider`
subclass that defines the method gets the same treatment on its authorization code exchange, refresh,
or `jwt-bearer` request.
`Provider.new` and `CrossAppAccessProvider.new` take the same keyword, held by `StorageBackedProvider` like
`authorization_request_validator`, so every bundled provider refuses a bad value before anything is stored.
The parameters go underneath the flow's own, so the SDK's values always win, and a key the SDK sets itself
(`Flow::RESERVED_TOKEN_REQUEST_PARAMS`) is refused rather than silently overridden: with `ArgumentError`
from the constructor, before any `client_information` is written, and again with `ArgumentError` from the flow,
before the token request is sent. Only Strings are accepted because `URI.encode_www_form` encodes other scalars
and Arrays in ways the caller did not write, and the provider keeps a frozen copy so a later change to
the caller's Hash cannot alter what is sent.
A Hash comparing keys by identity is refused too, since two equal keys are two entries there, sent twice
by a provider method or silently collapsed into one by the copy. The flow raises `ArgumentError` rather than
`AuthorizationError` because `MCP::Client::HTTP` treats a failed refresh as a reason to run the interactive flow,
which would then fail the same way after the user signed in.
Both refusals raise `Flow::InvalidTokenRequestParamsError`, a subclass of `ArgumentError`, so a caller can tell them
from an unknown keyword, and the copy duplicates keys as well as values, since `Hash` copies only keys
whose class is exactly `String`.
Fixes#554.
## How Has This Been Tested?
New tests cover every token request the parameters can ride (the `client_credentials` grant under
all three client authentication methods, the authorization code exchange, refresh, and `jwt-bearer`),
both refusal boundaries (the constructors of all three providers, and the flow for a provider defining the method),
and the transport surfacing a refused hook from a refresh attempt without starting the interactive flow.
All of them fail against the previous library.
## Breaking Changes
None. The keyword is optional and the hook is opt-in; a provider that does not define `token_request_params` sends
the same requests as before.
## Motivation and Context
json 3.0, released on 2026-09-07, accepts the options of `JSON.parse` as keywords only, and Faraday's json response middleware,
through 2.14.3, hands them over as a positional Hash, which Ruby 3 no longer converts. With both installed, every JSON body
the client receives fails inside that middleware, and `MCP::Client::HTTP` reports each request as an internal error.
Faraday's main branch passes the options as keywords, but no release carries that yet.
The client already parses streamed bodies and buffered SSE bodies itself; only a JSON body delivered
whole by an adapter without streaming support still went through the middleware. The client now parses that body too
and no longer registers the middleware, so every body takes `parse_json_buffer` and a malformed one answers
`:parse_error` whichever way it arrived. A JSON middleware added through the Faraday customizer block still works,
since a body it has parsed already is used as is.
## How Has This Been Tested?
A new test drives a buffered JSON response through a stand-in `JSON.parse` with the json 3.0 signature, options as keywords only,
so on Ruby 3 it failed with the middleware registered whatever json version is installed and passes now.
The existing buffered-body test keeps covering the plain path. The full suite passes on Ruby 3.0.7 with json 3.0.1 and faraday 2.14.3,
where five client tests failed before.
## Breaking Changes
None. A malformed JSON body delivered by an adapter without streaming support now raises `RequestHandlerError` with `error_type: :parse_error`,
as the streamed path already did, instead of `:internal_error` wrapping a `Faraday::ParsingError`.
## Motivation and Context
The ping utility says the receiver "MUST respond promptly with an empty response",
and a server may treat a missing answer as a stale connection and drop it. Both reference SDKs honor
that on the client side (the TypeScript protocol layer installs an automatic pong,
and the Python session answers `PingRequest` with an empty result), but this client answered
a server ping with Method not found over Streamable HTTP and ignored it entirely over stdio,
leaving long-lived legacy sessions vulnerable to a liveness-checking server.
Over HTTP, an unhandled `ping` is now answered with the empty result in `dispatch_server_request`.
The default deliberately does not live in `@server_request_handlers`: that registry's `any?` opens
the GET listening stream on connect, and a built-in pong must not change listener behavior -
a server can only ping on a stream that is already open. A handler registered via
`on_server_request("ping")` still wins.
Over stdio, the read loop now answers a ping frame inline and keeps waiting for its response.
Frames are told apart by shape rather than id: one carrying `method` is a request or notification,
never the awaited response, so a server-chosen ping id that collides with the awaited one is still answered -
and a request frame can no longer be returned to the caller as if it were the response.
Between requests nothing reads stdout, so a queued ping is answered when the next request starts reading,
which is inherent to the single-threaded stdio client. Other server-to-client requests over stdio stay
unsupported as documented.
The pong is best effort on both transports, in the ways the reference SDKs imply: a pong that cannot be written
over a broken stdin is dropped instead of failing the unrelated request whose response the loop is reading,
and a ping whose id is not a String or a Number - a shape the TypeScript and Python schemas reject outright -
is not answered with a pong: over stdio it is skipped entirely, and over HTTP it falls through to Method not found,
exactly as before this change.
The modern lifecycle removes `ping` altogether (SEP-2575), so this applies to handshake-lifecycle connections only.
## How Has This Been Tested?
New transport tests: over HTTP, a ping delivered on the SSE stream results in a POSTed empty-result response with
the ping's id, and a user-registered `"ping"` handler overrides the default; over stdio, a ping injected while
a response is awaited is answered on stdin and the original response still returns. Both fail without the change
(Method not found / no answer). Further tests cover the best-effort edges: a pong write failure over
a closed stdin leaves the awaited response intact, and a malformed-id ping is skipped over stdio
and answered with Method not found over HTTP. `bundle exec rake` (tests, RuboCop, and conformance baseline) passes.
## Breaking Changes
None. A server ping that previously received Method not found (or nothing) now receives the empty result
the specification requires.
## Motivation and Context
An MCP server chooses the authorization server its users sign in to. It names one in `authorization_servers`
in its Protected Resource Metadata, and states the scopes it wants in `scopes_supported`
or in the `WWW-Authenticate` challenge. Nothing binds either choice to the server's own identity.
No origin rule can settle this, because an authorization server is legitimately a different origin
from the resource it protects. Validating that a token was issued for the intended audience is a responsibility
the specification places on MCP servers rather than on clients, and there is no portable way for a client
to perform it either: access tokens are frequently opaque, and an authorization server is not required to honor
the `resource` parameter or to report an audience in the token response.
Two things follow from that, and they are separate.
The first is a judgement, and it belongs to whoever embeds this SDK, because an application often knows
which providers its users deal with. `authorization_request_validator` is handed an `AuthorizationRequest` describing
the authorization server, the scopes, the MCP server, and the RFC 8707 resource, and can refuse.
It is one object rather than keyword arguments so that later revisions of the specification can add to it
without changing the shape implementers wrote. It runs on all three grants, and on the authorization-code grant it
runs before dynamic client registration, which is why scope resolution moved above `ensure_client_registered`:
a refusal must not leave this client registered at an authorization server the host just rejected.
The second is not a judgement and is enforced here rather than asked about. `refresh!` rediscovers
the authorization server on every call, so the server named for a session can differ from the one
the stored tokens came from. SEP-2352 already binds client credentials to their issuer,
but that check passes when the issuer was never recorded and is deliberately skipped for a Client ID Metadata Document URL,
which is portable across authorization servers. The issuer that minted the tokens is now recorded with them,
and `refresh!` refuses to present them to a different one. The transport answers that refusal by running
a full authorization, which brings the new authorization server to the validator above. Tokens stored before
this carry no issuer and keep refreshing.
The hook decides whether to proceed, not what to ask for. The scopes reach the authorization server unchanged either way,
because the specification requires a client to treat the scopes in the challenge as authoritative for the operation,
and narrowing them silently would break that.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb` assert what the validator receives, that a refusal raises
before any registration request is sent and before the redirect handler runs, and that the `client_credentials`
and `jwt-bearer` grants consult it too. Others cover the issuer recorded on authorization, the refusal to refresh against
a different one, and that tokens stored without an issuer still refresh. A test in `test/mcp/client/oauth/http_oauth_test.rb`
drives the two halves together: a stale issuer makes the refresh fail, the transport reauthorizes, and the validator sees
the newly named authorization server while no refresh token is ever posted to it. Each of them fails with its half of
this change removed. `bundle exec rake` (tests, RuboCop, and conformance baseline) passes.
## Breaking Changes
Refreshing now fails when the authorization server named for a session differs from the one that issued the stored tokens,
and the caller reauthorizes instead. Tokens stored before this change carry no recorded issuer and are unaffected
until their next authorization. The validator itself is additive: it defaults to `nil`, and a provider that does not offer
it authorizes as before.
## Motivation and Context
`MCP::Client::HTTP` caps a single message from the server at 4 MiB, but the OAuth flow talks to
authorization endpoints over its own Faraday connection, and that one had no cap. Discovery,
dynamic client registration, and token responses were buffered in full and handed to `JSON.parse`,
so a server that answered an OAuth request with an endless body grew the client's memory for as
long as it kept sending.
`Flow` and `IDJAGTokenExchange` each build their own connection, so both needed the bound.
The new `BoundedBody` counts bytes in a Faraday `on_data` callback and refuses the response once
it passes `MAX_RESPONSE_BYTES`, which matches the 4 MiB of `MCP::Client::HTTP::MAX_MESSAGE_BYTES`
and `MCP::Client::Stdio::MAX_LINE_BYTES`. It hands back the status paired with the bounded body
rather than the Faraday response, so no later caller can reach the unbounded `response.body`.
Those bytes are counted after decompression. The default Net::HTTP adapter negotiates `Accept-Encoding`
itself and reads the body through `Net::HTTPResponse#inflater`, so a small compressed body that expands past
the cap is refused partway through the expansion. That holds only while the connection leaves
`Accept-Encoding` alone, which is now recorded in a comment on both `default_http_client` definitions.
An over-cap response is refused rather than truncated: a partial discovery or token document cannot be validated.
Protected resource metadata is the one place where refusing is not fatal, since any PRM discovery failure
already selects the legacy authorization path by design.
## How Has This Been Tested?
New unit tests in `test/mcp/client/oauth/bounded_body_test.rb` cover the streaming path,
the at-limit boundary, and the fallback for adapters that ignore `on_data`. One of them serves
a gzip body over a real socket rather than through WebMock, which returns a stubbed body verbatim
and never runs the inflater; it fails if the cap ever starts measuring compressed bytes. New tests in
`test/mcp/client/oauth/flow_test.rb` and `test/mcp/client/oauth/id_jag_token_exchange_test.rb` drive each of
the four request wrappers end to end with an over-cap body; all five fail without the cap in place.
## Breaking Changes
An OAuth endpoint response larger than 4 MiB is now rejected instead of parsed.
## Motivation and Context
Follow-up to https://github.com/modelcontextprotocol/ruby-sdk/issues/512#issuecomment-5285679761
A comment on #512 reported that results stay unstamped when a client negotiates `2026-07-28` through
the legacy `initialize` handshake: the SEP-2322 `resultType` stamp and the SEP-2549 cache hints are
both gated on the per-request `_meta` envelope, which such a connection never carries,
so strictly validating clients reject every result as missing the REQUIRED `resultType`.
The root cause sits upstream of the stamp. Per the SEP-2575 era model, an era is a property of
the protocol version itself: legacy versions establish a session via `initialize`
(`2025-11-25` and earlier), and modern versions carry their version on every request in `_meta` with
no handshake at all - the 2026-07-28 schema defines no `initialize`, and a request without the envelope
is malformed. The negotiation list of this server still contained `2026-07-28`, producing a hybrid state
the spec does not define and the reference SDKs refuse to construct: the TypeScript server negotiates
from `SUPPORTED_PROTOCOL_VERSIONS`, which stops at `2025-11-25`, and counter-offers its first entry;
the Python server negotiates from `HANDSHAKE_PROTOCOL_VERSIONS`, which stops there too,
and counter-offers `LATEST_HANDSHAKE_VERSION`.
`initialize` now negotiates from a new `SUPPORTED_HANDSHAKE_PROTOCOL_VERSIONS` list
(`2025-11-25` and earlier): a request for `2026-07-28`, or for a version this server does not know,
is counter-offered `2025-11-25`, exactly as both reference SDKs answer. A counter-offered client proceeds on
`2025-11-25`, where `resultType` does not exist and its absence is the correct shape,
resolving the reported rejection. `2026-07-28` stays reachable through `server/discover` and
the per-request envelope, where the stamps already apply. The `envelope &&` stamp gates are
intentionally unchanged: with the handshake capped, an envelope-less `2026-07-28` connection is
no longer constructible, so the gates are correct by construction.
The client side is symmetrized the same way, matching both reference SDKs:
the legacy handshake offers `LATEST_HANDSHAKE_PROTOCOL_VERSION` by default,
passing an explicitly modern `protocol_version` to the legacy connect raises `ArgumentError`
(validated before the stdio transport spawns its child process), and a server answering `initialize` with
a modern version is rejected like an unknown one. `:auto` forwards an explicitly modern version to
the discovery probe and never downgrades it into the legacy fallback: the probe's failure is
the real answer and propagates, instead of the fallback dying on the handshake guard.
The handshake rule itself lives in one place (`Configuration.reject_modern_handshake_version!`),
and the handshake list is derived from the stable and modern lists so the era partition cannot drift
when the next revision lands.
Two consequences are worth naming. The roots/sampling deprecation warnings move to the modern connect
on the client, the revision where SEP-2577 actually deprecates them, since the handshake can no longer land
on a deprecating version and the call site the warnings used to sit on had become unreachable.
On the server the answer is removal: `Configuration#protocol_version` scopes the handshake,
so it now accepts handshake versions only and rejects a modern pin with `ArgumentError` at construction.
Accepting one would configure nothing (a modern version has no handshake to pin),
and neither reference SDK carries a config value that is accepted but inert:
Python's negotiation has no knob at all, and every entry of the TypeScript server's `supportedProtocolVersions`
is consumed by its own era's mechanism. With no path left onto a deprecating revision,
the server-side deprecation warning plumbing became unreachable and is removed along with it.
Keying those warnings on a modern-era session instead was tried and rejected,
because `notify_log_message` is the SEP-2575 sanctioned delivery path on that wire and every log line
would then carry a deprecation warning for doing exactly what the revision prescribes
(a single test file produced over a thousand of them).
A session-bound request may still stamp `MCP-Protocol-Version: 2026-07-28` after being counter-offered,
and such a request continues to be served at the negotiated revision rather than rejected.
Sending the negotiated version is a SHOULD on the client, and the spec's `400 Bad Request` rule
covers a version the server does not support, which is not the case here: this server does serve `2026-07-28`,
through the other lifecycle. The session it is bound to decides, and a test now pins that reading along with
its consequence, which is that no `resultType` appears on those results.
Two details follow from the pin being handshake-scoped. Reading it back when nothing is set
now answers `LATEST_HANDSHAKE_PROTOCOL_VERSION` rather than the newest version of any era,
so the getter no longer hands out a value its own writer rejects and round-tripping
the setting keeps working; only `Server#validate!` reads that default,
through three comparisons that answer the same for either value, so nothing else moves.
And the rejection names its reason instead of listing the accepted versions,
because this is the error an upgrade from a release that accepted the value lands on,
which makes it the migration note a bare list would not be.
`MCP::ProtocolDeprecations` says in its own documentation that only the client emits these warnings now,
and that `LOGGING_MESSAGE` has no caller left. It stays public and callable: removing it would be
a breaking change for no gain.
The handshake examples in `docs/building-clients.md` and the shared `initialize_params` test helper
now use the handshake version as well, and the README section on `protocol_version` describes the pin as
handshake-scoped: handshake versions only, `ArgumentError` for a modern one, the handshake version as the default,
and `2026-07-28` reached through `server/discover` with no configuration needed.
## How Has This Been Tested?
New regression tests pin the reported scenario end to end: an `initialize` requesting `2026-07-28` is
counter-offered `2025-11-25`, locks the legacy era, and subsequent results carry no `resultType`
(the correct shape at that revision). Client-side tests cover the default `2025-11-25` offer,
the `ArgumentError` for an explicitly modern version on the legacy connect
(asserting no child process is spawned on the stdio transport), the rejection of a modern `InitializeResult`
on both transports, the `:auto` probe failure propagating for an explicitly modern version instead of
falling back, and the deprecation warning firing on modern connects declaring roots/sampling capabilities.
Counter-offer adoption gets its own test on both transports, since the server-side fix only resolves anything for
clients that honor a counter-offer, and this client is one of them: the offer is the latest handshake version,
the answer is an older one, and the connection speaks the answer afterwards
(over HTTP the next request's `MCP-Protocol-Version` header carries it). The existing tests could not tell adoption
from an echo, because every one of them had the server answer with the version the client had just offered.
Both new tests were confirmed to fail when the client is made to report its own offer instead.
Tests that pinned the previous dual-lifecycle negotiation were inverted or reworked:
the server tests asserting `2026-07-28` echoes and fallbacks now assert the counter-offer,
and the deprecation warning tests keyed on a legacy-negotiated `2026-07-28` now assert no warning fires.
The server-side deprecation tests that reached their state by calling `mark_initialized!` with a modern version,
or by pinning one in `Configuration`, were replaced by tests asserting no warning fires on those paths,
since no code path can produce the warning state any more; `Configuration` rejecting a modern pin has its own tests
on the constructor and the setter, asserting the reason in the message rather than the list of accepted values.
The default-pin test now also round-trips what it reads back into a fresh `Configuration`,
which is what the old default could not do. The default move was checked for neutrality outside
the suite as well, by building a server that uses every feature `Server#validate!` gates on that value
(`description`, `title`, `website_url`, `instructions`, a `$ref` input schema, and tool annotations)
and confirming all of them are still accepted.
## Breaking Changes
Servers no longer echo `2026-07-28` from `initialize`: clients that negotiated it through
the handshake are counter-offered `2025-11-25` and are served at that revision, matching
the TypeScript and Python servers. `Configuration.new(protocol_version: "2026-07-28")` now
raises `ArgumentError` (the pin scopes the handshake, which cannot land there);
the value was only accepted since v1.1.0, whose handshake behavior this change replaces anyway.
Reading `Configuration#protocol_version` with no pin set answers `2025-11-25` instead of `2026-07-28`;
nothing in this SDK behaves differently for either value, but code comparing that reader against
a literal will see the change. The client no longer offers modern versions on the legacy handshake
and rejects a modern `InitializeResult`. Server-side deprecation warnings for SEP-2577 features
no longer fire at all, because no negotiation or configuration path can put a connection on a deprecating revision;
the client-side warning on a modern connect replaces them.
## Motivation and Context
The OAuth client checked the scheme of every discovery URL but never checked where it pointed.
`Discovery.secure_url?` returns true for any `https` URL regardless of host, and the `resource_metadata` URL from
a `WWW-Authenticate` challenge is placed first in the candidate list, so a server answering
`401 Bearer resource_metadata="https://169.254.169.254/..."` had the client issue that request during discovery,
before the user approves anything. The same gap applied one hop deeper: a server that serves its own
Protected Resource Metadata can name any host in `authorization_servers`, and the endpoints in the document fetched
from there receive the dynamic client registration and the token request that carries the client credentials.
Two rules now apply to those URLs. Both run before the request is sent, and neither is configurable.
The `resource_metadata` URL must be on the MCP server's own origin. Protected Resource Metadata describes that server,
so a real deployment publishes it there, and requiring it means a challenge cannot aim the first request of the flow at
an unrelated host. RFC 9728 does not itself require this, so the SDK is deliberately stricter than the specification:
the range check below cannot recognize an internal host that is named rather than addressed, and this is the one URL
a server supplies directly.
The PRM `authorization_servers` entry and the `authorization_endpoint`, `token_endpoint`, and `registration_endpoint`
from Authorization Server metadata must not be IP literals in a private, loopback, link-local, or unique-local range,
which is the precaution RFC 9728 Section 7.7 asks clients to take. That check is skipped when the configured MCP server URL
is itself on such an address. Pointing a client at a private network is a deliberate act and its authorization server
usually lives on the same network, so `http://localhost` development and deployments that never leave a corporate network
keep working. Only a server reachable on the public internet is barred from steering the client inward.
A range check is only as good as its reading of the address, so the second rule also refuses hosts written in
the numeric IPv4 grammar `inet_aton` accepts and `IPAddr` rejects: one to four dot-separated parts, each hexadecimal,
octal, or decimal, with the last part filling the remaining bytes. `2130706433`, `127.1`, and `0x7f000001` all reach
127.0.0.1, and `0xa9fea9fe` reaches the cloud metadata address, so reading only the dotted-decimal spelling would refuse
`169.254.169.254` while admitting every alias of it. Those hosts are refused outright rather than decoded and
range-checked, because their value is resolver-dependent: a leading zero reads as octal on one platform and decimal on
another, which is the difference between 8.0.0.1 and 10.0.0.1 for `010.0.0.1`. Choosing a reading here would leave
whichever one was not taken as a way through, and nothing is legitimately addressed in this notation.
Hostnames are not resolved. A lookup here would be a second network request driven by the same untrusted input,
and the address it returned need not be the one the HTTP client connects to a moment later, so the check would read as
a guarantee it cannot make. `MCP::Client::OAuth::Flow` also documents why its Faraday connection has no redirect-following
middleware: every check runs against the URL as written, so a connection that follows a `3xx` on its own would reach hosts
these rules just refused.
## How Has This Been Tested?
- New unit tests in `test/mcp/client/oauth/discovery_test.rb` cover `same_origin?` (case-insensitive scheme and host,
explicit default ports, differing port/host/scheme, subdomains, malformed and hostless input) and `private_network_host?`
(every blocked range, IPv4-mapped IPv6 spellings, bracketed IPv6, `localhost` matched exactly, and public addresses and names).
One test documents that a named internal host reads as public, which is the deliberate limit of the predicate.
- Further unit tests cover the numeric spellings: packed integers, hexadecimal, and short forms that reach a blocked range,
and the ambiguous leading-zero forms whose value depends on the resolver. Removing the rule leaves them addressable,
which is what those tests fail on.
- New tests in `test/mcp/client/oauth/flow_test.rb` and `test/mcp/client/oauth/http_oauth_test.rb` drive both rules through `run!`,
`refresh!`, and the transport. They assert with `assert_not_requested` that no request was issued rather than only that an error
was raised, since nothing downstream can un-send one. One of them names the authorization server `https://0xa9fea9fe`, which
without the rule above is fetched. A further test runs a complete flow with the MCP server and the authorization server on
two loopback ports, which is what the carve-out exists for.
- `rake conformance` passes with all 22 auth scenarios green. Its harness runs the MCP server and the authorization server on
separate loopback ports and publishes PRM on the server's own origin, so it exercises exactly the shapes these rules must not break.
## Breaking Changes
A client whose MCP server is reachable on the public internet no longer follows a `resource_metadata` URL on a different origin,
and no longer contacts an authorization server or OAuth endpoint at a private IP literal or at a host written in the numeric
IPv4 notation above. All were previously allowed. Local development, private-network deployments, and the conformance suite
are unaffected.
## Motivation and Context
The SSE `retry:` field is chosen by the server, and `MCP::Client::HTTP` passed it to `sleep` unchanged in
both reconnection paths. `await_response_after_disconnect` runs on the calling thread, so a server that primes
a stream with an event id, closes it gracefully, and asks for a large `retry:` interval keeps that thread waiting
for as long as it likes. `MAX_RECONNECTION_ATTEMPTS` caps how many times the client reconnects, not how long
it waits before each attempt, and no I/O timeout covers a sleep.
The obvious fix, clamping `retry:` to a ceiling, is not available: the spec says a client
"MUST respect the `retry` field, waiting the given number of milliseconds before attempting to reconnect",
and reconnecting sooner than a server asked for is also the wrong direction to err in, since `retry:` is how
an overloaded server asks for room. Both reference SDKs pass the value through untouched.
What the spec does allow is waiting longer. The `retry` field it points at is the one WHATWG HTML defines,
whose reconnection algorithm reads "Wait a delay equal to the reconnection time of the event source. Optionally,
wait some more." It also leaves reconnecting at all a SHOULD, which this client already declines once
`MAX_RECONNECTION_ATTEMPTS` is reached. Both fixes below sit inside that room; neither shortens a wait.
`await_response_after_disconnect` now carries a deadline, `max_reconnection_wait:` seconds
(`MAX_RECONNECTION_WAIT`, 300, the same budget as `SSE_LISTENER_READ_TIMEOUT`). Before each attempt it compares
the delay the server asked for against the remaining budget, and stops reconnecting when honoring it in full
would run past the deadline. The server's interval is therefore either waited out exactly or not acted on at all,
and the calling thread is released as soon as the answer is known. On the reported case, a day-long `retry:`,
the thread now returns without sleeping at all.
Whatever is left of the budget also becomes the resumed stream's read timeout, so the bound covers a server
that accepts the GET and then sends nothing. That GET previously relied on whatever the Faraday adapter
defaults to, which is 60 seconds for Net::HTTP but need not exist at all for a caller-supplied adapter.
`listen_for_server_requests` already guarded its own GET this way with `SSE_LISTENER_READ_TIMEOUT`.
The other path has the opposite problem. `listen_for_server_requests` treats a graceful close as success and
resets `consecutive_failures`, so `retry: 0` never reaches the attempt cap and the listening stream reconnects
in a tight loop. A `MIN_RECONNECTION_DELAY_MS` floor of 100ms stops that, and is the "optionally, wait some more"
case exactly. That path gets no deadline: it runs on a thread this client owns and is meant to poll indefinitely
(the spec asks clients to "poll" a closed stream by reconnecting), so a long `retry:` there idles the SDK's own
listener rather than the embedding application.
`DEFAULT_RECONNECTION_DELAY_MS` and `MAX_RECONNECTION_ATTEMPTS` are unchanged and still match the Python SDK.
## How Has This Been Tested?
New tests in `test/mcp/client/http_test.rb` cover a day-long `retry:` releasing the calling thread without
sleeping, a delay that fits the budget still being waited out in full and resuming normally, a caller-supplied
`max_reconnection_wait:` stopping the resume with a message naming the budget, and the argument validation.
Both reconnection paths are covered for the unusable values a server can send: `retry: 0` is raised to the floor
on the resumption path and on the listening stream, and negative or non-numeric values (`-5000`, `abc`, `1e6`, `500ms`)
fall back to the default delay, since the SSE parser accepts only a run of digits. The existing reconnection tests,
whose `retry:` values fit the default budget, are unaffected.
`bundle exec rake` (tests, RuboCop, and conformance baseline) passes. The conformance `sse-retry` scenario scores
`client-sse-retry-timing`, which checks the reconnect happens neither early nor very late against a 500ms `retry:`;
since no wait is ever shortened, that check is unaffected by the size of the value it uses.
## Breaking Changes
A request whose resumption cannot complete within `max_reconnection_wait:` (300 seconds by default) now fails instead of
waiting however long the server asked for. Servers asking for intervals that fit the budget are unaffected.
Pass a larger `max_reconnection_wait:` if you expect longer.
## Motivation and Context
SEP-2243's custom-header half (MCP 2026-07-28) lets a tool annotate `inputSchema` properties with
`x-mcp-header` so intermediaries can route on argument values without parsing bodies: the client MUST
mirror each annotated argument of a `tools/call` into an `Mcp-Param-{Name}` header, encode values that
cannot ride as plain ASCII field values with the `=?base64?...?=` sentinel, and omit the header for
`null` or absent arguments. `MCP::Client::HTTP` sent only the standard `Mcp-Method`/`Mcp-Name` mirror
headers, so every `http-custom-headers` check of the 2026-07-28 conformance requirements fails.
The new `MCP::Client::McpParamHeaders` module ports the TypeScript SDK's `mcpParamHeaders` codec:
- `scan` walks a tool's `inputSchema` for declarations and validates every constraint the spec places
on them: RFC 9110 token names, case-insensitive uniqueness, primitive-typed declaring properties
(`number` is accepted alongside the spec's `string`/`integer`/`boolean` because the published
referee annotates `type: "number"` parameters, the same accommodation the TypeScript SDK makes),
and static reachability through a chain of `properties` keys only: an annotation under `items`,
the combinators, or `$defs` invalidates the whole tool definition.
- `build` resolves each declaration's path in the call's `arguments`, omits `null`/absent and
non-representable values (unsafe integers, non-finite floats, non-primitives), converts primitives
per the spec's rules, and encodes with the sentinel exactly where a plain ASCII field value
cannot carry the value (empty, edge whitespace, bytes outside visible ASCII, sentinel-shaped input).
`MCP::Client::HTTP` learns declarations from the `tools/list` responses passing through it (the same
source of truth the TypeScript SDK's response cache uses) and mirrors on each `tools/call` alongside
the existing `Mcp-Method`/`Mcp-Name` construction. Learning and mirroring exist on the modern
lifecycle only, matching both reference SDKs. An invalid tool definition mirrors nothing, per
the spec's guidance to send without custom headers when no reliable declarations are available;
a complete (uncursored, `nextCursor`-less) listing rebuilds the registry so declarations of
unlisted tools stop mirroring (the Python SDK's pruning), and the registry is capped
(`MAX_MCP_PARAM_TOOLS`, 1000) so a server rotating tool names cannot grow it without bound.
On the modern lifecycle, `MCP::Client#list_tools` and `#tools` also enforce the spec's MUST:
a tool definition whose `x-mcp-header` annotations violate the constraints is excluded from
the listing, with a warning naming the tool and the reason (the spec's SHOULD), so one malformed
definition does not block the valid tools - the same filtering the Python SDK's
`_absorb_tool_listing` and the TypeScript SDK's cached-listing finalize apply. A value that cannot
be represented as UTF-8 omits its header like the other non-representable values.
The README documents the mirroring and the exclusion under the lifecycle negotiation section.
The server-side validation half of the codec is a follow-up.
## How Has This Been Tested?
New `test/mcp/client/mcp_param_headers_test.rb` covers the scan constraint matrix (root and
non-reachable placements, empty/non-token/duplicate names, non-primitive types), the primitive
conversions (including `42.0` serializing as `42` and unsafe integers refusing), the encoding matrix
(plain pass-through, empty, non-ASCII, edge whitespace, CR/LF, sentinel-shaped input), and header
construction with nested paths and omitted values (including a value that cannot be represented
as UTF-8). `test/mcp/client/http_test.rb` drives the transport end to end over a modern connection:
a `tools/list` teaching the declarations, the following `tools/call` carrying the mirrored headers,
an invalid declaration mirroring nothing, a legacy connection learning nothing, and a complete
listing pruning the declarations of unlisted tools. `test/mcp/client_test.rb` covers the MUST-level
exclusion: the invalid definition dropped from `#tools` with the warning on a modern connection,
and listed unchanged on a legacy one. `bundle exec rake` is green.
## Breaking Changes
None. Requests to servers whose tools carry no `x-mcp-header` annotations are byte-for-byte unchanged,
and the new headers only appear for tools that declare them.
## Motivation and Context
Final step of the stateless lifecycle (SEP-2575, modelcontextprotocol/modelcontextprotocol#2575) for
the 2026-07-28 MCP spec release, now that the server core and both server transports can serve modern traffic.
Server side, `Server#discover` reaches its spec-final shape:
- `supportedVersions` advertises modern versions only, matching the TypeScript and Python SDKs:
legacy versions are negotiated via `initialize`, not selected from discovery. This also closes
an interop hazard of the interim response: auto-negotiating TS and Python clients treat
any `DiscoverResult` as proof of a modern server and do not fall back to `initialize`,
so advertising only legacy versions made them fail outright.
- The `ttlMs`/`cacheScope` cache hints are REQUIRED on `DiscoverResult` (unlike the opt-in SEP-2549 hints
on list and read results), so the spec defaults (`0`, `"private"`) fill in when the server was not configured with
`ttl_ms`/`cache_scope`, and the configured SEP-2549 values are reused otherwise.
- The server identity rides in the result `_meta` as the optional `io.modelcontextprotocol/serverInfo` stamp
instead of a top-level `serverInfo` field, following spec PR modelcontextprotocol/modelcontextprotocol#3002
(the TypeScript SDK stamps `_meta` the same way and the Python `DiscoverResult` carries no top-level
`serverInfo`, so the top-level placement was invisible to both). `Client#discover` and
the `server_implementation` reader read the `_meta` stamp with a top-level fallback for servers built
against the frozen SEP text, and the key is exposed as `RequestEnvelope::SERVER_INFO_META_KEY`.
Client side, both bundled transports learn the modern lifecycle, and `MCP::Client` negotiates it automatically by default:
- `MCP::Client#discover` sends `server/discover` and returns a `DiscoverResult` struct
(`supported_versions`, `capabilities`, `server_info`, `instructions`, `ttl_ms`, `cache_scope`).
It works before `connect`; the stdio transport's connect guard exempts `server/discover`
and spawns the subprocess on demand.
- `connect` gains `mode:` and defaults to automatic negotiation, joining the Python, Go, and C# SDKs
(the TypeScript SDK keeps a legacy default): transports whose `connect` declares `mode:`
(the bundled HTTP and stdio transports) receive `:auto`, which probes `server/discover`
and falls back to the legacy handshake on any discovery failure, including a successful discovery
without a mutually supported modern version (rollout tolerance for servers that answer discovery
while only serving legacy versions). Custom transports whose `connect` does not declare `mode:`
keep receiving the historical legacy call shape, detected by keyword introspection;
a bare `**kwargs` deliberately does not count, so wrappers and test doubles that absorb arbitrary keywords
stay on the legacy shape. An explicit `:modern`/`:auto` against such a transport raises `ArgumentError`
instead of silently downgrading.
- The mode vocabulary is `:legacy`/`:auto` (shared with the Python and TypeScript SDKs) plus an explicit `:modern`,
instead of folding a version-string pin into `mode` as Python and TypeScript do: this client has carried
the scalar `protocol_version:` keyword since the handshake landed, so a second version-bearing input would make
the API ambiguous about which one wins. `mode:` stays the strategy and `protocol_version:` stays the version,
the same orthogonal split as the Go and C# scalar version pins; Python's `mode="2026-07-28"` is expressed here
as `mode: :modern` with `protocol_version: "2026-07-28"`.
- An explicit legacy-generation `protocol_version` (e.g. `"2025-11-25"`) pins the legacy handshake without a probe,
so an explicitly requested version is never overridden by the default negotiation adopting the modern lifecycle.
`mode: :legacy` forces the classic handshake unconditionally; prefer it for spawn-per-invocation CLI tools
and when using server-initiated requests, which exist only on the legacy lifecycle.
- Because the raw `connect` return value and `server_info` mirror the wire result, their shape depends
on the negotiated era (`InitializeResult` vs `DiscoverResult`). New era-independent readers absorb that difference:
`MCP::Client#protocol_version` (negotiated or adopted version; backed by a new stdio transport reader and the existing HTTP one),
`#server_capabilities`, `#instructions`, and `#server_implementation`, which reads the spec-final `_meta`
`io.modelcontextprotocol/serverInfo` stamp with a top-level fallback and returns `nil` when a modern server
does not identify itself. `server_info` remains the permanent raw window to everything the readers do not cover.
- The stdio `server/discover` probe is bounded by a new `DEFAULT_DISCOVER_PROBE_TIMEOUT` (5 seconds, matching the C# SDK)
when no `read_timeout` was configured: a compliant legacy server answers the probe with `-32601` immediately,
but a non-compliant one that silently drops unknown methods must read as legacy evidence for the auto fallback
instead of blocking `connect` forever. Regular requests keep the unbounded default.
- In modern mode, the new shared `MCP::Client::ModernEnvelope` stamps the SEP-2575 `_meta` triple onto
every request (never onto notifications, whose `_meta` carries no envelope), reusing the reserved key names
from `MCP::RequestEnvelope`. The HTTP transport sends the matching `MCP-Protocol-Version` header and
keeps the existing `Mcp-Method`/`Mcp-Name` mirror headers; no `Mcp-Session-Id` is ever attached because `initialize`
is never sent.
- The conformance client pins `mode: :legacy`: the referee validates the legacy `initialize` handshake
and its scenario servers do not expect a preceding probe.
Resolves#389.
## How Has This Been Tested?
New tests in `test/mcp/server_test.rb` pin the required cache hints (spec defaults and configured SEP-2549 values);
the existing discover assertions across `server_test.rb` and both transport test files were updated to
the modern-only `supportedVersions`.
New tests in `test/mcp/client_test.rb` cover the `DiscoverResult` struct mapping, `ValidationError`/`ServerError`
on malformed and error responses, and the mode resolution contract: the `:auto` default on transports declaring `mode:`,
the unchanged legacy call shape for transports without it, the legacy pin for an explicit stable `protocol_version`,
`ArgumentError` for explicit non-legacy modes on transports without `mode:`, unknown-mode rejection,
and the era-independent readers against legacy results, modern results, the `_meta` `serverInfo` stamp, and absence.
New tests in `test/mcp/client/http_test.rb` cover modern adoption via discovery, envelope stamping with
the matching header on subsequent requests, the no-mutual-version failure, both auto-mode fallbacks,
and argument validation. New tests in `test/mcp/client/stdio_test.rb` cover pre-connect `server/discover`,
modern adoption with envelope stamping and no `initialize` frame, the auto-mode fallback, the probe timeout
default applying only while probing, and the fallback when a server never answers the probe.
## Breaking Changes
`server/discover` responses change shape (modern-only `supportedVersions` plus the required `ttlMs`/`cacheScope`);
this method has not shipped in a gem release yet, so no released behavior changes.
On the bundled HTTP and stdio transports, `MCP::Client#connect` without `mode:` now probes `server/discover` before
the legacy handshake: against legacy servers this adds one round trip and an unknown-method entry in their logs with
an unchanged final result, and once a server serves the modern lifecycle the connection adopts it, changing
the raw result shape from `InitializeResult` to `DiscoverResult`. Pass `mode: :legacy` or an explicit legacy-generation
`protocol_version` to keep the previous behavior unconditionally, or use the era-independent readers, which are stable
across both lifecycles. Custom transports without `mode:` and direct `transport.connect` calls are unaffected.
Warn when Roots, Sampling, or Logging APIs are used with MCP protocol version 2026-07-28 or newer.
Add a shared protocol deprecation helper, YARD deprecation notes, and regression tests covering warnings at and after the deprecation threshold and no warnings for older or never-established protocol versions.
Closes https://github.com/modelcontextprotocol/ruby-sdk/issues/390
Co-authored-by: Qlaw <noreply@qlaw.quick.shopify.io>
Client#tools/#list_tools built Tool objects without an annotations
field even though the server includes annotations in every
tools/list response. Add the reader and pass the raw hash through,
mirroring how output_schema is already handled.
## Motivation and Context
`MCP::Client::HTTP` buffers server bytes with no upper bound in two places:
- SSE responses are parsed incrementally, but the parser accumulates `data:` lines until
a blank line dispatches the event, so a server that never terminates an event grows
the buffer indefinitely. The abort-on-response signal does not help here, since it only fires
after a complete response event has been dispatched.
- Non-SSE (JSON) bodies accumulate in `SSEStream#buffer` chunk by chunk with no limit.
Both the POST response stream and the standalone GET listening stream are affected.
The stdio client already bounds server frames (`max_line_bytes:`, 4 MiB default)
and the server transports bound request bodies (`max_request_bytes:`, 4 MiB default);
this brings the HTTP client in line.
`MCP::Client::HTTP.new` gains `max_message_bytes:` (default 4 MiB), which caps the bytes buffered
for a single message - an SSE event or a JSON response body. External byte counting cannot tell
consumed-and-discarded bytes (comments, field names, delimiters) from consumed-and-retained ones,
so the check measures the parser's own String buffers after each chunk. An over-limit message raises
`RequestHandlerError` on the request path and stops the GET listening stream instead of reconnecting to
the same over-limit event.
## How Has This Been Tested?
New tests in `test/mcp/client/http_test.rb` cover the SSE and JSON rejection paths end-to-end,
the per-event reset (events that individually fit must not count against later ones),
the env-less `on_data` fallback, and the constructor validation. `bundle exec rake`
(tests, RuboCop, and conformance baseline) passes.
## Breaking Changes
Responses larger than 4 MiB are now rejected by default; pass a larger g`max_message_bytes:` to accept them.
## Motivation and Context
This repository does not track Gemfile.lock, so `bundle install` resolves to the latest RuboCop gems.
Upgrading rubocop-shopify from 2.x to 3.0.0 surfaces 8 new offenses because the shared config no longer
disables `Style/MutableConstant`, newly disables `Lint/RescueException` and `Naming/AccessorMethodName`,
and drops `AllowedPatterns` for `Naming/MethodName`. Upgrading rubocop itself to 1.88 surfaces one more offense
from the new `Style/ReduceToHash` cop.
This change fixes them as follows:
- Freeze mutable constants. Regexp constants are also flagged because `TargetRubyVersion` is 2.7,
where Regexp literals are not frozen.
- Remove inline disable directives that became redundant.
- Restore `AllowedPatterns: ['\Atest_']` for `Naming/MethodName` so `def test_` style test names
can reference class names such as `NoMethodError`.
- Swap out the frozen `SUPPORTED_STABLE_PROTOCOL_VERSIONS` constant in the protocol version fallback test
since Mocha cannot stub methods on frozen objects.
- Use `to_h` instead of `each_with_object` in `Server#index_resources_by_uri`.
Ref: https://rubygems.org/gems/rubocop-shopify/versions/3.0.0
## How Has This Been Tested?
`bundle exec rake` passes: 1402 runs, 0 failures, 0 errors, and RuboCop reports no offenses.
The conformance suite also passes against its baseline.
## Breaking Changes
None. Freezing these constants only affects code that mutates them in place, which has never been supported.
## Motivation and Context
The MCP Enterprise Managed Authorization extension (SEP-990, modelcontextprotocol/modelcontextprotocol#990,
accepted/final, published in the ext-auth repository) lets enterprise identity providers govern MCP authorization:
the client exchanges an IdP-issued ID token for an Identity Assertion Authorization Grant (ID-JAG) via
RFC 8693 token exchange at the IdP, then presents the ID-JAG to the MCP authorization server with
the RFC 7523 `jwt-bearer` grant, authenticating with `client_secret_basic`.
The `auth/cross-app-access-complete-flow` conformance scenario exercises the complete flow and previously failed
its two core checks (the Ruby client ran the authorization-code flow instead).
This mirrors the merged TypeScript SDK implementation (`requestJwtAuthorizationGrant` / `CrossAppAccessProvider` in
typescript-sdk; the Python SDK tracks the same work in the open python-sdk#1721), adapted to this SDK's provider design:
- New `MCP::Client::OAuth::IDJAGTokenExchange.request` performs the RFC 8693 exchange at the IdP token endpoint
(`subject_token_type` id_token, `requested_token_type` id-jag, `audience` = the MCP authorization server's issuer,
`resource` = the canonical MCP server URL) and validates that the response's `issued_token_type` is an ID-JAG
before returning the assertion. The ID-JAG itself is treated as opaque, as in the TypeScript SDK.
- New `MCP::Client::OAuth::CrossAppAccessProvider` declares `authorization_flow :jwt_bearer` and takes the assertion
from a callable (`call(audience:, resource:)`), so the common `IDJAGTokenExchange` case, enterprise secret stores,
and tests all plug in the same way (the TypeScript provider's assertion callback works identically).
The MCP AS credentials are stored as `client_secret_basic` client information.
- `Flow` dispatches `:jwt_bearer` alongside `:client_credentials`: discovery, issuer validation, and endpoint security checks
are shared with `run!`, then `run_jwt_bearer!` requests the assertion with the validated issuer as the audience and posts
the `jwt-bearer` grant through the existing `post_to_token_endpoint`.
- The conformance client builds a `CrossAppAccessProvider` when the harness injects `idp_id_token` (exchanging it at
`idp_token_endpoint` with `idp_client_id`, like the TypeScript and Python conformance clients),
and `auth/cross-app-access-complete-flow` is removed from `conformance/expected_failures.yml`.
## How Has This Been Tested?
- New `test/mcp/client/oauth/id_jag_token_exchange_test.rb` asserts the exact RFC 8693 form parameters on the wire
and the response validation: a non-ID-JAG `issued_token_type` is rejected, as are a missing `access_token`,
non-2xx responses, unparseable bodies, and non-object JSON.
- New `test/mcp/client/oauth/cross_app_access_provider_test.rb` covers the provider surface:
stored `client_secret_basic` credentials, the `:jwt_bearer` flow declaration, audience/resource passthrough to
the assertion callable, constructor validation (missing client_id, missing client_secret, non-callable assertion provider),
and storage delegation.
- New tests in `test/mcp/client/oauth/flow_test.rb` run the full grant against WebMock stubs: the token request carries
`grant_type=urn:ietf:params:oauth:grant-type:jwt-bearer`, the assertion, the RFC 8707 `resource`, and HTTP Basic credentials,
with no DCR and no authorization-code machinery; the assertion callable receives the validated issuer as `audience`
and the canonical server URL as `resource`; an empty assertion aborts before the token endpoint is contacted.
## Breaking Changes
None. `IDJAGTokenExchange` and `CrossAppAccessProvider` are new, and the `Flow` dispatch only activates for providers
that declare `authorization_flow :jwt_bearer`.
## Motivation and Context
A JSON-RPC message is an object, but two stdio-facing paths assumed that and raised
on a non-object value parsed from an incoming frame:
- `JsonRpcHandler.handle` maps each element of a batch array through `process_request`,
which reads `request[:id]` assuming a Hash. A non-object batch element (for example `[[]]`
or `[5]`) makes `[][:id]` raise `TypeError`. `handle_json` rescued only `JSON::ParserError`,
so the error escaped; over stdio it escaped the `StdioTransport#open` read loop.
The HTTP transport already rejects array bodies before dispatch, so this surfaced only on stdio.
- `MCP::Client::Stdio#read_response` parses each frame from the server and calls `parsed.key?("id")`,
which raises `NoMethodError` when the server emits a non-object frame.
Only `JSON::ParserError` was rescued, so one malformed line from the server escaped.
Both are robustness gaps: a malformed frame should be reported or skipped, not raise
an unhandled exception out of the transport.
- `process_request` now returns an `INVALID_REQUEST` error response for a non-object request
before touching `request[:id]`, so a malformed batch element becomes a normal per-element error.
- `handle_json` gains a last-resort `StandardError` rescue that returns an `INTERNAL_ERROR` response,
so an unexpected handling error still produces a JSON-RPC reply.
- `read_response` skips a non-object frame the same way it skips a frame without an id.
## How Has This Been Tested?
New tests in `test/json_rpc_handler_test.rb` cover non-object batch elements
(`[[]]`, `[5]`, `["x"]`, `[nil]`, `[true]`), a valid request followed by one non-object element,
and `handle_json("[[]]")` returning an error instead of raising. A test in
`test/mcp/server/transports/stdio_transport_test.rb` drives `open` with a `[[]]` line and
asserts it emits an error response without raising. A test in `test/mcp/client/stdio_test.rb`
has the server emit non-object frames before the response and asserts the client skips them
and still returns the response.
## Breaking Changes
None. A well-formed request, batch, or response is handled exactly as before;
only a non-object message now yields a JSON-RPC error on the server or is skipped by the client
instead of raising.
## Motivation and Context
Resolves the `elicitation-sep1034-client-defaults` client conformance scenario
(SEP-1034, https://github.com/modelcontextprotocol/modelcontextprotocol/issues/1034).
The Ruby HTTP client could not receive server-to-client requests at all:
it never opened the spec's standalone GET SSE listening stream, and SSE events that
were not responses were discarded. A server sending `elicitation/create` during a tools/call
(such as the conformance harness, which is built on the TypeScript SDK server)
either dropped the request silently or deadlocked the tool call waiting for an answer that
could never arrive.
This change adds three pieces:
### Server-to-client request dispatch
`MCP::Client::HTTP#on_server_request(method) { |params| ... }` registers a handler;
when a JSON-RPC request (a message with both `method` and `id`) arrives on any SSE stream,
the handler's return value is POSTed back to the server as the JSON-RPC `result`
(the server ACKs with 202 Accepted, per the transport spec).
Methods without a handler are answered with a `-32601` method-not-found error.
A handler may raise `MCP::Client::ServerRequestError` to answer with a specific JSON-RPC error code
(for example `-1` for a rejected sampling request, per the sampling spec),
mirroring the TypeScript SDK's `McpError` and the Python SDK's `ErrorData` return;
any other error is answered with a `-32603` internal error. In every case the server is not left waiting,
matching how the TypeScript and Python SDKs convert handler failures into JSON-RPC error responses.
### A standalone GET SSE listening stream
Registering a handler (once connected) opens the spec's listening stream on a background thread,
because servers deliver requests that are not tied to a client request on that stream -
the TypeScript SDK's `StreamableHTTPServerTransport` silently drops them when no GET stream is open.
Mirrors the TypeScript and Python SDK clients, which start listening right after the `initialize` handshake
without awaiting stream establishment. Reconnection semantics also follow both SDKs:
a gracefully closed stream is retried indefinitely after the server's `retry:` interval,
while consecutive connection failures (HTTP errors and idle read timeouts) stop the listener once
they reach the reconnection attempt cap, with a successful stream resetting the count;
a 405 stops immediately without retrying, since it is the spec's answer from a server that
offers no listening stream. The listening GET uses a 5-minute read timeout matching
the Python SDK's `sse_read_timeout` default. `close` terminates the thread.
### SEP-1034 defaults
`MCP::Client::Elicitation.apply_defaults` fills fields omitted from the elicitation content with
the `default` values declared in `requestedSchema` properties, never overwriting provided values
and skipping properties without a default. This follows the Python SDK, which applies defaults in
the elicitation callback; the TypeScript SDK's automatic `applyElicitationDefaults`
(gated on the `elicitation.form.applyDefaults` capability) is a possible follow-up.
`MCP::Client#on_elicitation` registers a handler for `elicitation/create` as a convenience.
The conformance client gains an `elicitation-sep1034-client-defaults` branch that connects with
`capabilities: { elicitation: {} }`, accepts the elicitation with defaults applied, and calls
the harness's `test_client_elicitation_defaults` tool; the scenario is removed from the expected failures baseline.
## How Has This Been Tested?
New unit tests covering: handler dispatch from a request's POST SSE stream with
the response body and 202 ACK verified, the `-32601` answer for unregistered methods,
the `-32603` answer for a raising handler, the custom-code answer when a handler raises
`ServerRequestError`, listener startup from both registration-after-connect and
connect-with-registered-handlers, listener shutdown after consecutive connection failures with
the count resetting after a successful stream and an immediate stop on 405,
and `apply_defaults` for all five SEP-1034 property types (string, integer, number, enum, boolean),
non-overwriting of provided values, omission of properties without defaults, and symbol-keyed schemas
## Breaking Changes
None. The listening stream and its background thread are created only when a server-request handler is registered;
clients that never call `on_server_request` / `on_elicitation` keep the existing single-request behavior.
## Motivation and Context
Both transports read a peer-controlled message fully into memory with no upper bound,
so a single unauthenticated message can allocate gigabytes and OOM the worker:
- `StreamableHTTPTransport#handle_post` did `request.body.read` with no size limit
before `JSON.parse`. A single ~512 MB POST grew a worker from 44 MB to 1.66 GB RSS
in the reporter's measurement. The path runs before session validation,
so it is reachable unauthenticated in both stateful and `stateless: true` modes.
- `StdioTransport` and `MCP::Client::Stdio` read frames with `IO#gets` and no `limit:`,
so a peer that never emits a newline grows a single String until the process is OOM-killed.
This matters when a host pipes an untrusted server's stdout into an unconstrained process.
The spec does not mandate a request size limit, and the reference SDKs vary
(the TypeScript SDK caps at a 4 MB default; Python/Go delegate to the web framework).
A finite default here bounds the allocation at the transport layer regardless of the deployment,
matching the TypeScript SDK's default.
- `StreamableHTTPTransport` gains `max_request_bytes:` (default 4 MiB). `handle_post`
rejects a declared `Content-Length` over the cap before reading, and also bounds
the actual read to one byte past the cap so a missing or spoofed `Content-Length`
(chunked transfer) is still caught, returning HTTP 413. `parse_request_body` now passes
`max_nesting:` (64) so a deeply nested body cannot exhaust the stack (complements the byte cap).
The constructor validates the new option as a positive Integer, since `nil` or a non-positive
value makes the underlying read unbounded and would silently disable the protection.
- The stdio `max_line_bytes:` bound (default 4 MiB) has since been merged upstream through
a separate advisory, so this change carries the remaining piece of the reported stdio fix:
an over-limit frame leaves leftover bytes in the pipe, desyncing the stream beyond recovery,
so `MCP::Client::Stdio` now closes the transport before raising and a later `send_request`
fails cleanly instead of parsing a truncated frame.
## How Has This Been Tested?
New tests in `test/mcp/server/transports/streamable_http_transport_test.rb` cover the 413 rejection
with and without `Content-Length`, the boundary body being accepted, the nesting-depth rejection,
and the constructor validation. The client stdio over-limit test now also asserts the transport
is closed afterward (`refute_predicate(transport, :connected?)`).
`bundle exec rake` (tests, RuboCop, and conformance baseline) passes. Verified end-to-end that
a 256 MB POST with no declared `Content-Length` is rejected with 413 without the transport reading
the whole body (a throttled `rack.input` that raises if read far past the cap is never tripped).
## Breaking Changes
None. The 4 MiB defaults comfortably fit a typical JSON-RPC message (a 4 MiB JSON string decodes to
roughly 3 MiB of base64 payload), and the new keyword arguments are additive and optional.
## Motivation and Context
CRuby's `IO#gets` without a limit reads until the next newline with no upper bound.
A peer that never emits a newline can therefore grow a single String until the process
is killed by the OS OOM killer.
This is a denial-of-service exposure (GHSA-7683-3w9x-ch42), identified during
a cross-SDK audit of the same unbounded-buffer pattern across the MCP SDKs.
It is most relevant when a host application spawns a sandboxed or untrusted MCP server
and pipes its stdout into an unconstrained host process, where a memory-capped peer
can exhaust the host.
Each frame is now capped at a configurable `max_line_bytes` (default 4 MiB,
large enough for any realistic frame including base64-embedded images,
and the value recommended in the advisory). A frame that reaches the limit without
a newline is treated as a transport error: the client raises, and the server reports
the error and closes the connection. A short final frame that ends at EOF without
a trailing newline is still accepted, so legitimate traffic is unaffected.
Both constructors validate `max_line_bytes:` as a positive Integer,
since `nil` or a non-positive value makes `IO#gets` read without an upper bound and
would silently disable the protection.
## How Has This Been Tested?
Server tests cover the `open` read loop stopping and reporting on an over-limit frame,
the `send_request` read loop raising on an over-limit response, and a valid final frame
without a trailing newline still being processed.
Client tests cover `read_response` raising on an over-limit response frame and
a normal response still round-tripping within a custom `max_line_bytes`.
Both transports also have tests rejecting invalid `max_line_bytes:` values
(`nil`, zero, negative, non-Integer) with an `ArgumentError`.
The full test suite and RuboCop pass.
## Breaking Changes
None. The default 4 MiB limit is far larger than any realistic JSON-RPC frame,
so existing well-behaved traffic is unaffected. The new `max_line_bytes:` keyword
on both transport constructors is purely additive and optional.
## Motivation and Context
SEP-2352 (modelcontextprotocol/modelcontextprotocol#2352, merged for the 2026-07-28 spec release) clarifies
authorization server binding and migration: clients MUST key persisted client credentials by the issuing
authorization server's issuer identifier, MUST NOT reuse credentials across different authorization servers,
and MUST re-register when the server's authorization server changes. CIMD `client_id`s (HTTPS URLs) are
explicitly portable across authorization servers, and a mismatch SHOULD surface an error rather than silently use
mismatched credentials.
The Ruby flow previously reused any stored `client_information` with a `client_id` unconditionally,
so a server that migrated to a new authorization server would have the old server's credentials
(and its dead tokens) replayed forever. This change follows the detect-change, invalidate,
and re-register approach that both reference SDKs converged on (typescript-sdk#2348/#2358, merged 2026-06-24;
python-sdk#2933/#2936/#2946, which uses the same proactive compare-before-reuse design as this change)
while keeping the 4-method storage contract intact by stamping the binding into the persisted hash:
- Successful Dynamic Client Registration now persists the credentials with an `"issuer"` member set to
the validated AS metadata `issuer` (which `ensure_issuer_matches!` has already pinned to the discovery URL).
- `Flow#ensure_client_registered` reuses stored credentials only when the stored issuer matches the current one.
Credentials without an issuer binding (data persisted by older SDK versions, or user-supplied pre-registered credentials)
are bound to the current issuer on first use. A portable CIMD `client_id` is reused and re-bound.
Any other issuer mismatch discards the stale registration and its tokens (tokens minted by the old AS are dead at the new one)
and re-registers via CIMD/DCR.
- `Flow#refresh!` raises `AuthorizationError` instead of replaying another authorization server's credentials at the token endpoint;
`MCP::Client::HTTP#attempt_refresh` already rescues that error and falls back to the full flow, which performs
the discard-and-re-register.
- The `client_credentials` grant (machine-to-machine) reads static pre-registered credentials without going through
`ensure_client_registered`, so it would have silently sent another authorization server's credentials after a migration.
`run_client_credentials!` now surfaces an `AuthorizationError` when the stored `issuer` mismatches the current authorization server,
implementing the spec's "SHOULD surface an error" (the TypeScript SDK raises `AuthorizationServerMismatchError` here).
Re-registration is not an option for pre-registered m2m credentials, so the operator must update the stored credentials;
credentials without a recorded issuer keep working unchanged.
Two adjacent hardenings from the reference implementations were checked and need no change here:
the legacy-fallback issuer stamp is self-consistent because this SDK's fallback registers at the same origin it
uses as the issuer (the cross-origin never-reached-AS binding python-sdk#2946 closed cannot arise),
and preserving a non-rotated `refresh_token` across refreshes already exists via `preserve_refresh_token`.
The TypeScript SDK's redirected-to-issuer callback gate is not adopted: the RFC 9207 `iss` validation (SEP-2468) covers that mix-up leg.
Resolves#385.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb`:
- stored credentials with a matching issuer skip DCR
- an issuer mismatch re-registers and persists the new `client_id` with the new issuer
- the stale registration's tokens are cleared before re-registration (observed by aborting the flow at the DCR step)
- legacy credentials without an issuer (string- and symbol-keyed) are reused and bound to the current issuer on first use
- a CIMD `client_id` with a mismatched issuer is reused without DCR and re-bound
- fresh DCR persists the issuer binding
- `refresh!` succeeds with a matching stored issuer and raises (without contacting the token endpoint) with a mismatched one
- the `client_credentials` grant succeeds with a matching stored issuer and raises (without contacting the token endpoint) with
a mismatched one
All existing flow, HTTP OAuth, and provider tests pass unchanged.
## Breaking Changes
None for the documented storage contract: `client_information` hashes gain an additional `"issuer"` member that storages persist opaquely,
and credentials stored without one keep working via first-use binding. Behavior changes only in the previously broken case where
the authorization server changed, which now re-registers (or, for static machine-to-machine credentials, surfaces an error) instead of
replaying the old server's credentials.
## Motivation and Context
SEP-2549 (modelcontextprotocol/modelcontextprotocol#2549, merged for the 2026-07-28 spec release) adds a `CacheableResult`
shape with `ttlMs` (freshness lifetime in milliseconds, max-age semantics, 0 = do not cache) and `cacheScope`
(`"public"` or `"private"`, whether shared intermediaries may cache) to `ListToolsResult`, `ListPromptsResult`,
`ListResourcesResult`, `ListResourceTemplatesResult`, and `ReadResourceResult`, complementing the `listChanged` notifications.
The field shape follows the Python SDK's implementation (python-sdk#2824, `ttlMs` + `cacheScope` with `ttlMs: 0` /
`cacheScope: "public"` defaults; the TypeScript SDK's earlier `ttl`-seconds prototype #2070 was superseded by this shape).
Because this SDK negotiates protocol versions up to 2025-11-25, where the fields do not exist, emission is opt-in:
when neither `ttl_ms` nor `cache_scope` is configured, responses are serialized exactly as before. The fields become REQUIRED
in 2026-07-28; a follow-up can auto-emit defaults once that version enters `SUPPORTED_STABLE_PROTOCOL_VERSIONS`.
- `MCP::Server.new` gains `ttl_ms:` and `cache_scope:` keywords with validating writers modeled on `page_size=`
(`ttl_ms` must be nil or a non-negative Integer; `cache_scope` must be nil, `"public"`, or `"private"`).
- A private `apply_cache_metadata` wraps the five emission points. When the user sets only one of the two values,
the other is filled with the spec defaults (`ttlMs: 0`, the only universally safe freshness value, and `cacheScope: "public"`,
the spec and Python default).
- A `resources_read_handler` may return a full `{ contents:, ttlMs:, cacheScope: }` hash to override the server-level hints per result;
the documented bare-contents return shape keeps working unchanged.
- The client's `ListToolsResult` / `ListPromptsResult` / `ListResourcesResult` / `ListResourceTemplatesResult` structs gain
`ttl_ms` and `cache_scope` members populated from the response fields.
Resolves#387.
## How Has This Been Tested?
New tests in `test/mcp/server_test.rb`:
- with `ttl_ms: 5000`, all four list results carry `ttlMs: 5000` and the filled `cacheScope: "public"` default
- with only `cache_scope: "private"`, `resources/read` carries `ttlMs: 0`
- with neither configured, list and read results omit both fields (wire-format regression)
- the hints appear alongside `nextCursor` when paginating
- a `resources_read_handler` returning `{ contents:, ttlMs: 60_000 }` overrides the server-level value while the missing `cacheScope` is filled
- invalid writer values (`-1`, `1.5`, `"internal"`) raise `ArgumentError`
New tests in `test/mcp/client_test.rb` assert all four list result structs expose `ttl_ms` / `cache_scope`,
and that both are nil when the server omits the fields.
## Breaking Changes
None. Emission is opt-in, the new constructor keywords default to nil, and the client structs gain additive members.
## Motivation and Context
The MCP `io.modelcontextprotocol/oauth-client-credentials` extension
(SEP-1046, modelcontextprotocol/modelcontextprotocol#1046) specifies
two client authentication methods for the `client_credentials` grant:
`client_secret_basic` and the RECOMMENDED `private_key_jwt`
(RFC 7523 Section 2.2 JWT client assertion). The previous commit added
the grant with secret-based authentication; this adds the JWT method,
which is what the `auth/client-credentials-jwt` conformance scenario exercises.
This mirrors the merged implementations in the TypeScript SDK
(`PrivateKeyJwtProvider`, typescript-sdk#1157) and the Python SDK
(`PrivateKeyJWTOAuthProvider` / `SignedJWTParameters`, python-sdk#1663),
adapted to this SDK's provider design:
- New `MCP::Client::OAuth::JWTClientAssertion` builds the RFC 7523 compact
JWS with openssl, keeping the SDK free of a JWT gem dependency
(the TypeScript and Python SDKs use jose and PyJWT). Claims follow SEP-1046:
`iss` and `sub` carry the client_id, `aud` carries the authorization
server's issuer identifier, plus `exp` (300-second lifetime, matching both SDKs),
`iat`, and a unique `jti`. ES256 and RS256 are supported; ES256 signatures are
converted from OpenSSL's ASN.1 DER form to the raw 64-byte `r || s` encoding
JWS requires (RFC 7518 Section 3.4).
- `ClientCredentialsProvider` accepts
`token_endpoint_auth_method: "private_key_jwt"` with `private_key:`
(PEM string or `OpenSSL::PKey::PKey`) and a required `signing_algorithm:`
(no default, so an algorithm mismatch with the server's
`token_endpoint_auth_signing_alg_values_supported` fails loudly at construction;
both reference SDKs also take the algorithm explicitly).
The key stays on the provider and is never written to `storage`;
a throwaway assertion is signed at construction to fail fast on an unparseable key
or a key/algorithm mismatch.
- `Flow#post_to_token_endpoint` sends `client_assertion_type` and a freshly
signed `client_assertion` for `private_key_jwt`,
using the `ensure_issuer_matches!`-validated issuer as the audience,
and omits `client_id` from the body per SEP-1046
(identity travels in the assertion's claims).
- The conformance client builds a `private_key_jwt` provider
when the harness injects `private_key_pem`, defaulting the algorithm to
ES256 like the TypeScript and Python conformance clients,
and `auth/client-credentials-jwt` is removed from
`conformance/expected_failures.yml`.
Scope notes: only ES256 and RS256 are supported for now (the TypeScript and
Python SDKs accept whatever their JWT libraries support);
adding further algorithms is additive. There is also no injection point yet for
externally signed assertions (the TypeScript SDK's `StaticPrivateKeyJwtProvider` and
the Python SDK's `assertion_provider` callback cover KMS/HSM-held keys);
that is a separate follow-up.
## How Has This Been Tested?
New `test/mcp/client/oauth/jwt_client_assertion_test.rb` covers the JWS construction:
header and RFC 7523 claims, unpadded base64url segments,
ES256 signature round-trip verification (raw -> DER -> `OpenSSL::PKey::EC#verify`),
RS256 verification, PEM and parsed-key input, lifetime override, unique `jti` per assertion,
and rejection of unsupported algorithms, key/algorithm mismatches
(including a P-384 key with ES256), unparseable PEM, and public-only keys.
New tests in `test/mcp/client/oauth/client_credentials_provider_test.rb` cover
the provider surface: `private_key_jwt` construction, the key and
secret never reaching `client_information`, required `private_key` / `signing_algorithm`,
rejection of a simultaneous `client_secret`, fail-fast on key/algorithm mismatch,
and `client_assertion(audience:)` producing a JWT with the expected claims.
A new test in `test/mcp/client/oauth/flow_test.rb` runs the full grant against WebMock stubs
and asserts the token request carries `grant_type=client_credentials`,
the RFC 7523 `client_assertion_type`, an assertion whose `iss`/`sub` are the client_id
and whose `aud` is the issuer, the RFC 8707 `resource`, and neither `client_id` nor
any secret in the body or headers.
`bundle exec rake` passes; the `auth/client-credentials-jwt` conformance scenario
passes 7/7 checks and the baseline check passes with its expected-failure entry removed.
## Breaking Changes
None. `client_secret:` becomes optional on `ClientCredentialsProvider` only
in the signature; it is still required for the secret-based methods, and all
existing construction paths behave unchanged.
## Motivation and Context
SEP-2468 (modelcontextprotocol/modelcontextprotocol#2468, merged for the 2026-07-28 spec release) recommends
that authorization servers include the RFC 9207 `iss` parameter in authorization responses and requires MCP clients
to validate a present `iss` against the expected issuer before redeeming the authorization code.
This mitigates mix-up attacks in multi-IdP setups, where an attacker-controlled authorization server could otherwise capture
a code minted by an honest server.
This mirrors the TypeScript SDK's approach (typescript-sdk#2272, with typescript-sdk#1957 as the reference implementation),
adapted to the Ruby provider contract:
- `Provider`'s `callback_handler` may now return `[code, state, iss]` in addition to the existing `[code, state]`.
The 3-element form opts into validation; returning `iss = nil` asserts the caller inspected the authorization response
and found no `iss`.
- `Flow#run!` validates the issuer after the `state` check and before `exchange_authorization_code`,
implementing the RFC 9207 Section 2.4 rules: a present `iss` must equal the AS metadata `issuer` exactly
(the value `ensure_issuer_matches!` already pinned to the discovery URL); a nil `iss` from a 3-element callback is rejected
when the AS metadata advertises `authorization_response_iss_parameter_supported: true`; a legacy 2-element callback skips the check,
so every existing integration keeps working. On any violation the flow aborts with `AuthorizationError` before
the code reaches a token endpoint.
- The conformance client now returns the 3-element form, plumbing `iss` through from the redirect URL.
Resolves#386.
## How Has This Been Tested?
New tests in `test/mcp/client/oauth/flow_test.rb`:
- a matching `iss` completes the flow and persists tokens
- a mismatched `iss` raises `AuthorizationError` and never contacts the token endpoint (`assert_not_requested` on the token POST)
- a nil `iss` with `authorization_response_iss_parameter_supported: true` raises without contacting the token endpoint (fail closed)
- a legacy 2-element callback completes even when the AS advertises `iss` support (backward compatibility)
- a nil `iss` without the advertisement completes
- a mismatched `iss` is rejected even without the advertisement (validate-when-present is unconditional)
`bundle exec rake` (tests, RuboCop, and conformance baseline with the 3-element conformance callback) passes.
## Breaking Changes
None. The 2-element `callback_handler` contract continues to work unchanged; issuer validation activates only
when a callback opts in by returning the 3-element form.
## Motivation and Context
Resolves the `sse-retry` client conformance scenario (SEP-1699,
https://github.com/modelcontextprotocol/modelcontextprotocol/issues/1699).
Per SEP-1699, a server may close a request's SSE stream right after a priming event
(an event carrying an `id:`) without delivering the response, expecting the client
to treat the graceful close like a network failure: wait the server-specified
`retry:` interval, then reconnect with an HTTP GET carrying `Last-Event-ID`
so the server can replay the pending response on the resumed stream.
The Ruby client previously read the entire SSE body to EOF and parsed it afterward,
so it had no notion of per-event state (`id:`, `retry:`) or reconnection,
and the scenario failed all three checks (graceful reconnect, retry timing, `Last-Event-ID`).
`MCP::Client::HTTP#send_request` now consumes responses incrementally
via Faraday's `on_data` streaming callback, feeding SSE chunks to `event_stream_parser`
as they arrive while buffering plain JSON bodies as before. A new internal `SSEStream`
tracks the last received event id, the `retry:` reconnection delay,
and the awaited JSON-RPC response; once the response arrives, a held-open stream is
abandoned via an internal control-flow exception since servers may never close it.
When a stream closes gracefully after a priming event but before the response,
the client sleeps for the `retry:` interval (default 1000ms when the server sent none),
then issues a GET with `Accept: text/event-stream`, the session headers, and `Last-Event-ID`,
for up to 2 attempts. The defaults match the Python SDK's `DEFAULT_RECONNECTION_DELAY_MS` and
`MAX_RECONNECTION_ATTEMPTS` (`streamable_http.py`); the TypeScript SDK's `StreamableHTTPClientTransport`
(`streamableHttp.ts`) likewise lets the `retry:` field override its backoff and reconnects only when
a priming event was received and no response has arrived.
The public behavior of `send_request` is unchanged: same return values, same error mapping,
and a stream that closes without a priming event still raises the "No valid JSON-RPC response found in SSE stream" error
without reconnecting. Because the previous implementation read `response.body` and therefore worked with any Faraday adapter,
a fallback keeps that compatibility: when nothing was parsed during streaming, the body is read from `response.body`
(adapters without `on_data` support, e.g. the Faraday test adapter) or from the buffered chunks
(Faraday < 2.1, which invokes `on_data` without `env`).
The conformance client gains an `sse-retry` branch that calls the harness's `test_reconnection` tool,
and the scenario is removed from the expected failures baseline.
## How Has This Been Tested?
New unit tests covering: reconnection with `Last-Event-ID` after a primed graceful close including the `retry:` wait,
the default 1000ms delay when `retry:` is absent, raising after the reconnection attempt cap with `Last-Event-ID`
advancing across attempts, no reconnection for unprimed streams, and the non-streaming fallbacks
(JSON and SSE responses through the Faraday test adapter, which ignores `on_data`, plus buffered SSE chunks
when `on_data` receives no `env`)
## Breaking Changes
None. The `send_request` contract is unchanged; SSE bodies are now parsed incrementally instead of after EOF,
and reconnection only activates when the server opts in by sending a priming event.
## Motivation and Context
The MCP specification requires an `initialize` request followed by `notifications/initialized`
before any other interaction. Issue #334 makes that handshake explicit on the stdio client,
matching the Python SDK (`ClientSession.initialize()`) and TypeScript SDK (`Client.connect(transport)`).
The change was staged to avoid a hard break. Phase 1 (#336) added `MCP::Client::Stdio#connect`
while keeping an implicit-init compatibility shim on the first `send_request`.
Phase 2 (#338) emitted a deprecation warning when that shim ran. The warning has shipped since 0.16.0,
so this final phase removes the shim.
## How Has This Been Tested?
`send_request` now raises a `RuntimeError` when `connect` has not been called, and no longer
auto-starts the subprocess. `connect` is the sole entry point that spawns the process and
performs the handshake, which avoids leaving an orphaned subprocess behind.
The stdio test suite was reworked to call `connect` explicitly, a regression test was added for
the new guard, and `rake test` passes (1145 runs, 0 failures).
## Breaking Changes
Stdio clients that send requests without calling `MCP::Client#connect` now raise a `RuntimeError`
instead of silently initializing. Call `client.connect` before the first request.
Closes#334
Koichi ITO
Junyuan Zheng
Ates Goral
rickreyhsig-wealthbox