## 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
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
SEP-2322 (modelcontextprotocol/modelcontextprotocol#2322, merged for the 2026-07-28 spec release)
introduces Multi Round-Trip Requests: instead of issuing in-flight server-to-client JSON-RPC requests,
a server answers with a result whose `resultType` is `"input_required"`, carrying an `inputRequests` map
(of `sampling/createMessage`, `roots/list`, and `elicitation/create` request shapes) and
an opaque `requestState`; the client fulfills the requests and re-issues the original request with
`inputResponses` and the echoed `requestState`.
The wire contract (the `resultType` discriminator and the `inputRequests`/`requestState` shape)
stayed stable across all three closed TypeScript prototype iterations (typescript-sdk#2062/#2065,
the v2-stateless stack, and #2251) and the Python draft (python-sdk#2322), but the server-side
suspend/resume mechanism is still unsettled in both SDKs (typescript-sdk#2251 was put on hold on 2026-06-08).
This change therefore implements only the stable, additive vocabulary and the client-side recognition,
leaving server emission and automatic resumption for a follow-up once the reference design lands:
- New `MCP::ResultType` module with `COMPLETE` and `INPUT_REQUIRED` constants documenting the `resultType` values.
- `MCP::Client` raises the new `MCP::Client::InputRequiredError` (exposing `input_requests`, `request_state`,
and the raw `result`) when any response carries `resultType: "input_required"`, instead of silently returning
a non-final result as if it were the answer. The check lives in the shared request path,
so every client method is covered. Servers on stable protocol versions never emit `resultType`,
so default behavior is unchanged.
Part of #382.
## How Has This Been Tested?
New tests in `test/mcp/client_test.rb`:
- `call_tool` raises `InputRequiredError` for an `input_required` result and exposes `input_requests`,
`request_state`, and the full raw result
- `call_tool` returns normally when `resultType` is `"complete"` and when it is absent
(wire-compat regression for stable-protocol servers)
- `list_tools` also raises for `input_required` results, proving the recognition covers the shared request path
`bundle exec rake` (tests, RuboCop, and conformance baseline) passes.
## Breaking Changes
None for spec-compliant stable servers, which never send `resultType`. A response that does carry
`resultType: "input_required"` now raises `MCP::Client::InputRequiredError` instead of being returned as
a final result, which was always a misinterpretation of the draft semantics.
## Motivation and Context
The server-side half of MCP `notifications/cancelled` shipped earlier and lets handlers
observe cancellation via `server_context.cancelled?` / `raise_if_cancelled!`.
This PR delivers the client-side equivalent that was deferred at the time:
an `MCP::Client` user can now cancel a request they have already issued and have
the calling thread wake up, matching the Python SDK
(`anyio.CancelScope`) and TypeScript SDK (`AbortSignal`) ergonomics.
The recommended pattern is to pass an `MCP::Cancellation` token into the request method,
run the request on a worker thread, and call `cancellation.cancel(reason:)` from another thread.
The cancelling thread sends `notifications/cancelled` to the server, and the calling thread is
woken up with `MCP::CancelledError`:
```ruby
cancellation = MCP::Cancellation.new
Thread.new do
client.call_tool(name: "slow_tool", arguments: {}, cancellation: cancellation)
rescue MCP::CancelledError
# cleanup
end
cancellation.cancel(reason: "user pressed cancel")
```
For low-level use, `Client#cancel(request_id:, reason:)` sends the notification without managing
the calling thread, and `Client#generate_request_id` lets callers pre-allocate an id before kicking off
a request on another thread. The `request_id:` and `cancellation:` keywords are accepted by
every request method (`tools`, `list_tools`, `resources`, `list_resources`, `resource_templates`,
`list_resource_templates`, `prompts`, `list_prompts`, `call_tool`, `read_resource`, `get_prompt`,
`complete`, `ping`).
When `cancellation:` is supplied, the actual blocking `transport.send_request` runs on a worker thread;
the calling thread waits on a `Queue` woken either by the response or by the cancel signal
(whichever arrives first - the same race contract as the server-side `StreamableHTTPTransport#cancel_pending_request`).
On a normal completion the `on_cancel` hook is deregistered so a late cancel does not emit a stray `notifications/cancelled`.
The worker thread is *not* force-killed when a cancel wins the race; it stays blocked on the underlying I/O until
the transport actually returns (or the user closes it). For `Client::HTTP` the leak resolves as soon as
the server sends any response; for `Client::Stdio` the user may need to call `client.transport.close`
if the server stops responding entirely.
`Client::Stdio` and `Client::HTTP` gain `send_notification(notification:)` so `Client#cancel` can deliver
the JSON-RPC notification through the existing transport plumbing. Custom transports that do not implement
`send_notification` cause `Client#cancel` to raise `NoMethodError`.
Ref: https://modelcontextprotocol.io/specification/2025-11-25/basic/utilities/cancellation
## How Has This Been Tested?
`test/mcp/client_test.rb` covers `Client#cancel` payload (with and without `reason`),
`Client#generate_request_id` returning distinct UUIDs, every request method threading `request_id:` through,
and the full `cancellation:` flow:
- Returns the response when no cancel happens (no behaviour regression for callers that do not pass a token).
- Pre-cancelled token raises `MCP::CancelledError` immediately and never reaches the transport
(no stray request, no stray notification).
- Mid-flight cancel raises `MCP::CancelledError` carrying the supplied reason and sends `notifications/cancelled`
through the transport.
- Late cancel after a normal completion does not emit a stray notification
(the `on_cancel` hook is deregistered in the `ensure` block).
`test/mcp/client/stdio_test.rb` covers `send_notification` writing the JSON line through the spawned process
and returning `nil` without waiting for a response.
`test/mcp/client/http_test.rb` covers `send_notification` POSTing the body, tolerating HTTP 202 Accepted,
and surfacing Faraday errors as `RequestHandlerError`.
## Breaking Change
None. All new keywords (`request_id:`, `cancellation:`) on request methods are optional and default to `nil`.
Existing callers that do not pass them get the original synchronous behaviour. Custom transports that already
implement `send_request(request:)` continue to work; only callers of `Client#cancel` need a transport
that responds to `send_notification`, and the failure mode is a clear `NoMethodError` rather than silent breakage.
## Motivation and Context
SEP-2133 (modelcontextprotocol/modelcontextprotocol#2133, merged for
the 2026-07-28 spec release) establishes the extensions framework for MCP:
both `ClientCapabilities` and `ServerCapabilities` gain an optional `extensions`
member keyed by reverse-DNS extension identifiers
(e.g. `"io.modelcontextprotocol/tasks"`, `"com.example/feature"`), with arbitrary
extension-defined configuration objects as values and an empty object meaning
"supported with no settings". Official extensions such as MCP Apps (SEP-1865)
and the Tasks extension (SEP-2663) are layered on this field.
This mirrors the shape the TypeScript SDK merged (typescript-sdk#1630):
plain declaration and passthrough, no registrar API and no key-format validation
(the naming convention is documented instead).
- `MCP::Server::Capabilities` gains `support_extensions` (repeated calls merge),
accepts an `:extensions` key in its constructor hash, and includes `extensions`
in `to_h`. The class was previously dead code: it was never required and
`Server.new` only took plain hashes. It is now required by `lib/mcp/server.rb`,
and `Server.new(capabilities:)` accepts either a plain Hash (as before) or
a `Capabilities` instance.
- Server-declared extensions appear in the `initialize` result;
extensions the client declares during `initialize` were already stored verbatim and
are readable via `Server#client_capabilities[:extensions]` and
`ServerSession#client_capabilities[:extensions]` (now covered by tests).
- `MCP::Client#connect(capabilities:)` already passes capabilities through verbatim;
its documentation now covers the `extensions` member.
Resolves#378.
## How Has This Been Tested?
- New `test/mcp/server/capabilities_test.rb` covers the previously untested
`Capabilities` class: empty default, constructor round-trip, extensions via
constructor and `support_extensions`, merge semantics, nil tolerance,
and omission from `to_h` when never declared.
- New tests in `test/mcp/server_test.rb` assert that the `initialize` result
carries declared extensions (from both a plain hash and a `Capabilities` instance)
and that client-declared extensions are readable via `Server#client_capabilities`
and `ServerSession#client_capabilities`.
## Breaking Changes
None. `extensions` is additive and appears on the wire only when declared;
servers constructed with plain capability hashes behave exactly as before.
## Motivation and Context
SEP-414 (modelcontextprotocol/modelcontextprotocol#414, merged for
the 2026-07-28 spec release) documents OpenTelemetry trace context propagation
conventions for MCP: the un-prefixed `_meta` keys `traceparent`,
`tracestate`, and `baggage` are reserved (an explicit exception to
the reverse-DNS prefix rule) so trace context can flow between MCP clients and
servers per the W3C Trace Context and Baggage specifications.
This follows the TypeScript SDK's approach (typescript-sdk#2270):
guarantee `_meta` passthrough, export constants for the reserved key names,
and lock the behavior in with regression tests and documentation, without adding
an OpenTelemetry dependency (the Python SDK's python-sdk#2381 makes
`opentelemetry-api` a hard dependency instead, which conflicts with
this SDK's keep-dependencies-minimal policy):
- New `MCP::TraceContext` module exposing `TRACEPARENT_META_KEY`,
`TRACESTATE_META_KEY`, `BAGGAGE_META_KEY`, and `META_KEYS`.
- The server side already passes incoming request `_meta` to tool and prompt
handlers untouched via `server_context[:_meta]`; new regression tests pin
that guarantee for the three reserved keys.
- Every `MCP::Client` request method (`call_tool`, `read_resource`,
`get_prompt`, `complete`, `ping`, and the `list_*` methods) gains
a `meta:` keyword so Ruby clients can inject trace context (or any other
`_meta` entries) into outgoing requests; per SEP-414, trace context
should flow on every request, not only tool calls. The caller's hash is
never mutated. On `call_tool`, `progress_token` takes precedence over
a `progressToken` entry in `meta`, and an empty merge result omits `_meta`
entirely, preserving the existing wire format.
- README documents the convention and how to bridge the values to a tracing
system such as the `opentelemetry-ruby` gems.
Scope is intentionally client-to-server: server-initiated requests
(`sampling/createMessage`, `roots/list`, `elicitation/create`) do not accept
`meta:` yet; propagating trace context on those is a separate follow-up.
Resolves#374.
## How Has This Been Tested?
- New `test/mcp/trace_context_test.rb` pins the exact reserved key names and
the frozen `META_KEYS` list.
- New tests in `test/mcp/server_test.rb` assert that `tools/call` and
`prompts/get` deliver `traceparent`, `tracestate`, and `baggage` (alongside
`progressToken`) to handlers through `server_context[:_meta]` unchanged.
- New tests in `test/mcp/client_test.rb` cover the `meta:` keyword: the
trace keys are sent in `_meta` on `call_tool` and `read_resource`,
a table-driven test exercises the remaining request methods (`tools/list`,
`resources/list`, `resources/templates/list`, `prompts/list`,
`prompts/get`, `completion/complete`, `ping`), `progress_token` overrides
a `progressToken` entry in `meta` without duplicating the key,
the caller's `meta` hash is not mutated, and requests without `meta:`
serialize exactly as before (wire-format regressions for both the empty `meta`
hash and the no-params list request).
## Breaking Changes
None. `MCP::TraceContext` and the `meta:` keyword are purely additive, and
requests without `meta:` serialize exactly as before.
`#tools`, `#resources`, `#resource_templates`, and `#prompts` each repeated
the same loop to follow `next_cursor` and collect every page, differing only
in the `list_*` method called and the items field read from each page. Move
that loop into a single private `fetch_all_pages` helper so the four methods
are one-liners and the cursor-cycle guard lives in one place.
Behavior is unchanged; the existing `MCP::Client` list tests cover it.
## Motivation and Context
The MCP Authorization spec (2025-11-25) requires clients to support
Protected Resource Metadata discovery (RFC 9728), Authorization
Server Metadata discovery (RFC 8414), Dynamic Client Registration,
and OAuth 2.1 Authorization Code grant with PKCE (S256). The Ruby SDK
previously had no client-side OAuth support: the HTTP transport raised
`RequestHandlerError` on a 401 with no recovery, and 21 `auth/*` scenarios
were listed as known failures in `conformance/expected_failures.yml`.
This aligns the Ruby SDK with the Python and TypeScript SDKs,
both of which expose a pluggable OAuth client provider that drives
the full discovery + DCR + authorization + token exchange flow.
`MCP::Client::OAuth::Provider` mirrors that surface: callers supply
`client_metadata`, a `redirect_uri`, and pluggable `redirect_handler`
/ `callback_handler` hooks plus a token/client information storage.
`MCP::Client::OAuth::InMemoryStorage` is provided as a default.
`MCP::Client::HTTP` accepts a new optional `oauth:` keyword. When present,
the transport attaches `Authorization: Bearer` to every request,
and on a 401 parses `WWW-Authenticate` for the `resource_metadata` URL
and `scope` challenge, drives the discovery + DCR + authorization code flow
through the provider, and retries the failed request once with the acquired token.
Spec compliance details:
- The `WWW-Authenticate` parser handles multiple challenges
(e.g. `Basic ..., Bearer ...` or `Bearer ..., DPoP ...`), extracting only
the parameters that belong to the Bearer challenge.
- The PRM `resource` value is required to cover the MCP server URL
(same scheme/host/port, with the PRM path as a prefix of the server path)
before the flow continues, preventing redirection of issued tokens to a different audience.
- Both authorization and token requests always include a `resource`
parameter (RFC 8707), defaulting to a canonicalized form of
the MCP server URL when PRM does not advertise one.
- `client_secret_basic`, `client_secret_post`, and `none` token endpoint
authentication methods are supported. When pre-registered client information
specifies no `token_endpoint_auth_method`, the transport defaults to
`client_secret_basic` per RFC 6749 §2.3.1 an dthe TS/Python SDK convention.
Pre-registered client credentials supplied via `Storage#save_client_information`
with either string or symbol keys are honored, skipping DCR.
- Scope resolution follows the spec order: the `WWW-Authenticate` challenge scope wins first,
then PRM `scopes_supported`, and `Provider#scope` is the last-resort fallback only
if neither is supplied (the provider-supplied scope must not pre-empt server-advertised scope).
- Token endpoint error responses (RFC 6749 §5.2) are parsed: a 4x with
`error: "invalid_grant"` raises `Flow::InvalidGrantError`,
so `MCP::Client::HTTP` can discard the stored refresh token only when
the AS truly says it is dead. Generic `AuthorizationError`
(5xx, network failures, other error codes) leaves the refresh token
intact, so a transient AS outage does not force interactive reauth
on the next attempt.
- The OAuth `state` parameter is compared via
`OpenSSL.fixed_length_secure_compare` (with a `bytesize` guard) to
prevent timing-based discovery of the expected value.
- The 401 retry guard is a request-scoped local variable, so an MCP server
that keeps returning 401 is surfaced as an error after one
retry rather than triggering an infinite re-authorization loop.
## How Has This Been Tested?
Unit tests cover PKCE generation, multi-challenge `WWW-Authenticate` parsing,
PRM and Authorization Server metadata URL builders, the full Flow orchestrator
(success path, state mismatch, missing PKCE support, skipping DCR for both string
and symbol-keyed preregistered client information, `client_secret_basic`
token endpoint authentication, PRM `resource` mismatch rejection, fallback to
the server URL when PRM omits `resource`, scope resolution preferring PRM
`scopes_supported` over `Provider#scope`, default `client_secret_basic` for
confidential clients without an explicit `token_endpoint_auth_method`,
and the new `InvalidGrantError` vs generic `AuthorizationError` split for
token endpoint rejections), and the HTTP transport behavior
(401 recovery + retry, no-provider fallthrough, no infinite loop on repeated 401,
no infinite loop on flow failure, refresh-token retention on transient 5xx from
the token endpoint).
Conformance: `bundle exec rake conformance` newly passes 16 `auth/*`
scenarios beyond the existing baseline, including
`auth/metadata-default`, `metadata-var{1,2,3}`,
`scope-from-www-authenticate`, `scope-from-scopes-supported`,
`scope-omitted-when-undefined`, `scope-retry-limit`,
`token-endpoint-auth-{basic,post,none}`, `pre-registration`,
`resource-mismatch`, and `offline-access-not-supported`. Remaining
`auth/*` scenarios stay in `expected_failures.yml`.
`bundle exec rake test rubocop` is clean.
## Breaking Changes
None. `MCP::Client::HTTP#initialize` accepts a new optional `oauth:`
keyword that defaults to `nil`, preserving existing behavior. When unset,
the transport raises `MCP::Client::RequestHandlerError` on a 401 exactly as before.
## Motivation and Context
This commit implements Phase 1 of 3 for #334.
The MCP specification requires an `initialize` request followed by
a `notifications/initialized` notification before any other interaction.
PR #327 added `MCP::Client#connect` and `MCP::Client::HTTP#connect`
to expose this handshake explicitly for the HTTP transport,
but stdio remained on its private `initialize_session` lazy-init path,
inconsistent with the Python SDK (`ClientSession.initialize()`) and
TypeScript SDK (`Client.connect(transport)`),
both of which require an explicit handshake call regardless of transport.
The implicit init path on the first `send_request` is
preserved as a non-breaking compatibility shim. Public API added on `Stdio`:
- `connect(client_info:, protocol_version:, capabilities:)` performs the
handshake, validates the negotiated `protocolVersion` against
`MCP::Configuration::SUPPORTED_STABLE_PROTOCOL_VERSIONS`,
caches the `InitializeResult`, and is idempotent.
- `connected?` reports handshake completion.
- `server_info` exposes the cached `InitializeResult`.
Documentation and examples are updated so new users learn the explicit pattern
from the start.
## How Has This Been Tested?
Fifteen regression tests cover: explicit handshake, `server_info` caching,
idempotence, custom keyword arguments, JSON-RPC error response, missing
or non-Hash `result`, unsupported protocol version with state rollback,
state rollback when the `notifications/initialized` write fails,
retry after a failed handshake, and the `connected?` / `server_info` lifecycle.
The pre-existing stdio tests pass without modification, verifying that
the implicit-init compatibility path still works.
## Breaking Changes
None for the typical "implicit init via `client.tools` / `client.call_tool`" usage.
Existing stdio clients keep working unchanged.
Three observable behavior changes for code that inspects transport state directly:
- `Client#connected?` for a never-initialized stdio client returns `false`
(previously fell through to a `true` default via the `respond_to?` fallback).
- `Client#server_info` for stdio returns the cached `InitializeResult`
after the handshake (previously always `nil` via the fallback).
- The implicit handshake path now validates the server's negotiated
protocol version, raising `RequestHandlerError` for unsupported versions.
Production servers that return one of the supported versions are unaffected;
this closes a pre-existing spec-conformance gap on stdio.
Per the Streamable HTTP spec, if the server returns an Mcp-Session-Id
header during `initialize`, the client MUST include it on subsequent
requests. Capture the session ID and protocol version from the
`initialize` response and attach them automatically on subsequent
POSTs.
Per the Protocol Version Header section of the spec, the client MUST
also include `MCP-Protocol-Version` on all subsequent requests so the
server can respond based on the negotiated protocol version.
Map 404 responses to a new `SessionExpiredError` (a subclass of
`RequestHandlerError` for backward compatibility) and clear local
session state so callers can start a fresh session with a new
`initialize` request, as required by the spec.
- https://modelcontextprotocol.io/specification/2025-11-25/basic/transports#session-management
- https://modelcontextprotocol.io/specification/2025-11-25/basic/transports#protocol-version-header
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
## Motivation and Context
The MCP specification defines the `ping` utility for verifying that the peer of
a connection is still responsive. The Ruby SDK server side already replies to
incoming `ping` requests with an empty result, but `MCP::Client` had no public API
to send a `ping` request. Users had to build the JSON-RPC payload themselves and
call the transport directly.
This adds a client-side counterpart to the existing server handler and aligns
the Ruby SDK in spirit with the Python and TypeScript SDKs, which expose
`ClientSession.send_ping` and `Client.ping` respectively. Those SDKs validate
the response envelope via type schemas (`EmptyResult` / `EmptyResultSchema`) and raise
their validation library's generic exception (Pydantic's `ValidationError` / Zod's `ZodError`).
The Ruby client applies a Hash type check on `result`
(matching Python's behavior of requiring a dict while allowing arbitrary contents)
and raises a new `MCP::Client::ValidationError` for malformed responses,
keeping `MCP::Client::ServerError` reserved for JSON-RPC error responses.
## How Has This Been Tested?
Client tests cover:
- request structure (method is `ping`, no `params`)
- empty result on success
- `ServerError` on JSON-RPC error response
- `ValidationError` on a response missing `result`
- `ValidationError` on a `result` of the wrong type (e.g., String)
- propagation of transport-level errors raised by `transport.send_request`
The existing server-side `ping` handler tests continue to pass unchanged.
## Breaking Changes
None. `MCP::Client#ping` and `MCP::Client::ValidationError` are purely additive.
The server-side `ping` handler behavior is unchanged.
## Motivation and Context
The MCP specification defines cursor-based pagination for list operations that
may return large result sets:
https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/pagination
Pagination allows servers to yield results in smaller chunks rather than all at once,
which is especially important when connecting to external services over the internet.
The Ruby SDK previously returned complete arrays for all list endpoints
(`tools/list`, `resources/list`, `prompts/list`, `resources/templates/list`)
without pagination support. This adds cursor-based pagination.
### Server-side
A new `MCP::Server::Pagination` module is introduced (mixed into `MCP::Server`)
that provides the `paginate` helper for slicing a collection by cursor and
a `cursor_from` helper that extracts the cursor from the request params
while rejecting non-Hash inputs with `-32602 Invalid params` per the specification.
`MCP::Server.new` accepts a new `page_size:` keyword argument.
When `nil` (the default), all items are returned in a single response,
preserving the existing behavior. When set to a positive integer,
list responses include a `nextCursor` field if more pages are available.
`Server#page_size=` is a validating setter that rejects anything other than
`nil` or a positive `Integer`, raising `ArgumentError` on invalid inputs.
The constructor routes through the setter, so both `Server.new(page_size: 0)`
and `server.page_size = -1` raise.
Cursors are string tokens carrying a zero-based offset, treated as opaque by
clients. Cursor inputs are validated to be strings per the MCP spec;
invalid cursors (non-string, non-numeric, negative, or out-of-range) raise
`RequestHandlerError` with error code `-32602 (Invalid params)` per the spec.
### Client-side: two complementary APIs
The SDK exposes two API shapes for listing, each serving a different use case:
1. **Single-page with cursor** (`client.list_tools(cursor:)`,
`list_resources`, `list_resource_templates`, `list_prompts`): each call issues
one JSON-RPC request and returns a result object (`MCP::Client::ListToolsResult` etc.)
carrying the page items and an optional `next_cursor`.
These methods match the single-page-with-cursor convention used by the Python SDK
(`session.list_tools(params=PaginatedRequestParams(cursor=...))`)
and the TypeScript SDK (`client.listTools({ cursor })`). The method name and
the `cursor` parameter name are identical across the three SDKs,
so pagination code translates directly between languages.
2. **Whole-collection** (`client.tools`, `client.resources`, `client.resource_templates`,
`client.prompts`): auto-iterates through all pages and returns a plain array of items,
guaranteeing the full collection regardless of the server's `page_size` setting.
The auto-pagination loop tracks previously seen cursors in a set and exits if the server
revisits any of them, guarding against both immediate repeats and multi-cursor cycles
(e.g. `A -> B -> A`). This mirrors Rust SDK's `list_all_*` convenience methods,
though the Ruby names are preserved from the pre-pagination 0.13.0 API for backward compatibility.
Future rename to `list_all_*` is left as a TODO in the source.
Result classes are `Struct`s named to mirror Python SDK's `ListToolsResult` /
`ListPromptsResult` / etc. to align naming with other SDKs. Each struct exposes
its page items (e.g. `result.tools`), an optional `next_cursor` for continuation,
and an optional `meta` field mirroring the MCP `Result` type's `_meta` response field
so servers that decorate list responses do not lose metadata through the client.
### Ruby-specific ergonomics
`Server.new(page_size:)` and the `Pagination` module are Ruby-specific.
The Python and TypeScript SDKs do not expose a built-in `page_size` helper;
developers there re-implement cursor slicing inside each handler.
In Ruby, setting `page_size:` on the server is enough for the SDK to handle
the slicing across the four built-in list endpoints.
### README
A Pagination section documents both the server-side `page_size:` option and
the client-side iteration patterns, including an explicit note that each `list_*` call
is a single JSON-RPC round trip whose response size depends on the server's `page_size`,
and that `client.tools` / `.resources` / `.resource_templates` / `.prompts` return
the complete collection when needed.
## How Has This Been Tested?
- Added tests for the `Pagination` module (`test/mcp/server/pagination_test.rb`),
server-side pagination (`test/mcp/server_test.rb`), and client-side pagination
(`test/mcp/client_test.rb`).
- Added and existing tests pass. `rake rubocop` is clean and `rake conformance` passes.
## Breaking Changes
None. This is a new feature addition. Existing code continues to work unchanged:
`page_size` defaults to `nil` on the server (returns all items, no `nextCursor`),
and the client's existing `tools` / `resources` / `resource_templates` / `prompts` methods
continue to return complete arrays by transparently iterating through pages.
## Motivation and Context
The MCP specification defines `completion/complete` for providing autocompletion
suggestions for prompt arguments and resource template URIs.
The Ruby SDK previously had only a no-op handler that returned empty results,
with no way for users to define custom completion logic.
This aligns the Ruby SDK with the Python and TypeScript SDKs,
both of which support user-defined completion handlers.
## How Has This Been Tested?
Server tests cover: default handler, custom handler for `ref/prompt` and `ref/resource`,
context argument passing, 100-item truncation, and error responses for nonexistent prompts,
nonexistent resource templates, and invalid ref types.
Client tests cover: request structure, context parameter inclusion,
and fallback when result is missing.
## Breaking Changes
None. The existing default no-op handler behavior is preserved.
The `completion_handler` method is purely additive. The only behavioral change
is that `completion/complete` requests now validate that the referenced prompt
or resource template exists before calling the handler,
returning an `invalid_params` error for unknown references.
## Motivation and Context
Client methods (`tools`, `resources`, `resource_templates`, `prompts`, `read_resource`, `get_prompt`, `call_tool`)
silently swallowed JSON-RPC error responses by falling back to empty defaults. This did not conform to JSON-RPC 2.0,
which clearly distinguishes error responses from success responses.
Both the Python SDK (`MCPError`) and TypeScript SDK (`ProtocolError`) raise exceptions on error responses.
The Ruby SDK was the only one silently discarding them.
Introduces a common `request` method that handles JSON-RPC request construction and error checking in one place,
replacing the duplicated `transport.send_request` calls across all client methods.
## How Has This Been Tested?
Added tests for each affected method verifying that `ServerError` is raised with the correct `code`, `message`,
and `data` attributes.
## Breaking Changes
The previous behavior of silently returning empty defaults on server errors did not conform to JSON-RPC 2.0.
Error responses should be surfaced to callers, not swallowed.
Callers that relied on the silent fallback behavior will need to rescue `MCP::Client::ServerError`.
## Motivation and Context
`Client#call_tool` previously required an `MCP::Client::Tool` object to call a tool.
This made the API harder to use compared to other MCP SDK implementations,
which accept a tool name string directly:
- Python SDK: `session.call_tool(name, arguments)` accepts a name string.
https://github.com/modelcontextprotocol/python-sdk/blob/v1.26.0/src/mcp/client/session.py#L370
- TypeScript SDK: `client.callTool({ name, arguments })` accepts a name string.
ccb78f2/packages/client/src/client/client.ts (L834)
## How Has This Been Tested?
Updated existing tests and added new tests.
## Breaking Change
No. This change adds a `name:` parameter so callers can pass a tool name string
directly without looking up a `Tool` object first. The existing `tool:` parameter
continues to work for backward compatibility.
## Motivation and Context
The `MCP::Client` currently only supports HTTP transport (`MCP::Client::HTTP`).
To achieve parity with other MCP SDKs (Python, TypeScript, C#) which provide
stdio client transports for spawning and communicating with server subprocesses,
the Ruby SDK needs a stdio client transport.
https://modelcontextprotocol.io/specification/2025-11-25/basic/transports#stdio
This enables building MCP clients that launch server processes and communicate
via stdin/stdout using newline-delimited JSON-RPC 2.0 messages.
## How Has This Been Tested?
Added tests for process spawning, protocol initialization handshake,
notification handling, error handling, and transport close lifecycle.
## Additional context
Enabled the `Lint/IncompatibleIoSelectWithFiberScheduler` cop in `.rubocop.yml`
to detect accidental use of `IO.select` instead of `IO#wait_readable`.
## Motivation and Context
`lib/mcp.rb` currently declares all `require_relative` statements in one place.
As a result, Server and Client are both loaded, the stdio and Streamable HTTP
transports are both loaded, and Tool, Prompt, and Resource are all loaded,
regardless of which components are actually used.
These components are selected by the user depending on their use case,
so loading everything upfront is unnecessary.
Using `autoload` for selected constants defers loading until the constant
is actually referenced, so only the subsystems required by the user are loaded.
## How Has This Been Tested?
All existing tests pass unchanged.
## Breaking Change
None. This change only defers loading of unused components.
## Motivation and Context
The MCP specification defines `notifications/progress` for reporting incremental progress
during long-running tool operations. The Ruby SDK did not yet support this, so tools had no way to
send progress updates to clients. This caused the `tools-call-with-progress` conformance test to fail.
This adds an `MCP::ServerContext` wrapper that provides a `report_progress` method on
`server_context`. Tools call `server_context.report_progress(value, total:, message:)` to send
notifications back to the client. The method is a no-op when no `progressToken` was provided,
so tools can call it unconditionally without checking for a token.
This design is consistent with the TypeScript and Python SDKs, which provide progress
reporting through a context object rather than a separate parameter.
On the client side, `Client#call_tool` now accepts a `progress_token:` parameter that sets
`_meta.progressToken` in the request.
Ref: https://modelcontextprotocol.io/specification/latest/server/utilities/progress
## How Has This Been Tested?
Added comprehensive tests in `test/mcp/server_progress_test.rb` covering `notify_progress`,
tool integration with progress, block-defined tools, `**kwargs` tools, and no-op behavior
without a token.
Added client tests for `progress_token:` parameter inclusion and omission.
Added `test/mcp/server_context_test.rb` test for non-Hash `server_context` preservation
when `_meta` is present.
Conformance: `tools-call-with-progress` removed from expected failures.
## Breaking Change
`server_context` is now always an `MCP::ServerContext` instance when passed to tools,
even if the server has no context configured. Code that checks `server_context ?` to
detect a nil context will need to be updated, as `ServerContext` is always truthy.
`ServerContext` delegates method calls to the underlying context object via
`method_missing`, so `server_context[:key]` and other accessor patterns continue to work.
In practice, this is unlikely to affect users. A tool that declares `server_context:`
is opting in to use the context; if the server has no context configured, that is a
server configuration issue rather than something the tool should handle with a nil check.
