Replace all occurrences of ServerRequest[*CallToolParams] and other
concrete instantiations with CallToolRequest and the like.
Make the XXXRequest types aliases, to preserve the convenience of
generics for the internal machinery (see shared.go, for example.)
I will expand the aliases in a followup PR.
Change the design of tool handlers by removing genericity from the common path.
- `ToolHandler` gets the args as a `json.RawMessage`. Using Server.AddTool does no unmarshaling or schema validation.
- `ToolHandlerFor`, installed with `AddTool`, are the only generic pieces.
TODO:
uncomment and fix some tests
If there is a TokenInfo in the request context of a
StreamableServerTransport, then propagate it through to the
ServerRequest that is passed to server methods like callTool.
Fixes#317.
A few problems with reconnection cropped up in the review of PR #307.
We should allow for the hanging GET to fail with StatusMethodNotAllowed.
This simply means that the server does not support sending notifications
or requests over the GET, which is allowed in the spec.
Also, we should fix the initial delay of the hanging GET request: it
should start with 0 delay. Fix the math for this and subsequent
attempts. Incidentally, this makes the tests take 3s on my machine, down
from 9s.
Also address some comments from #307.
Several improvements for the stateless streamable mode, plus support for
a 'distributed' (or rather, distributable) version of the stateless
server.
- Add a 'Stateless' option to StreamableHTTPOptions and
StreamableServerTransport, which controls stateless behavior.
GetSessionID may still return a non-empty session ID.
- Audit validation of stateless mode to allow requests with a session
id. Propagate this session ID to the temporary connection.
- Peek at requests to allow 'initialize' requests to go through to the
session, so that version negotiation can occur (FIXME: add tests).
Fixes#284
For #148
Implement the concurrency model described in #26: notifications are
synchronous, but calls are asynchronous (except for 'initialize'). To
achieve this, implement jsonrpc2.Async(ctx) to signal asynchronous
handling. This is simpler to use than returning ErrAsyncResponse and
calling Respond, and since this is an internal detail we don't need to
worry too much about whether it's idiomatic.
Add tests that verify both features, for both client and server.
Also:
- replace req.ID.IsValid with req.IsCall
- remove the methodHandler type as we can just use MethodHandler
Fixes#26
Handlers and client/server methods take a single request argument
combining the session and params. This slightly simplifies the signature
for handlers, since there is no longer an often-ignored session
argument.
But more importantly, it opens the door to adding more information in
requests, such as auth info and HTTP request headers.
For #243.
As described in #272, there is really no reason for transports to be
closed structs with constructors, since their state must be established
by a call to Connect. Making them open structs simplifies their APIs,
and means that all transports can be extended in the future: we don't
have to create empty Options structs just for the purpose of future
compatibility.
For now, the related constructors and options structs are simply
deprecated (with go:fix directives where possible). A future CL will
remove them prior to the v1.0.0 release.
For #272
Support stateless streamable sessions by adding a GetSessionID function
to StreamableHTTPOptions. If GetSessionID returns "", the session is
stateless, and no validation is performed. This is implemented by
providing the session a trivial initialization state.
To implement this, some parts of #232 (distributed sessions) are copied
over, since they add an API for creating an already-initialized session.
In total, the following new API is added:
- StreamableHTTPOptions.GetSessionID
- ServerSessionOptions (a new parameter to Server.Connect)
- ServerSessionState
- ClientSessionOptions (a new parameter to Client.Connect, for symmetry)
For #10
In jsonprc2_test.go, binder.Bind starts a goroutine.
That goroutine begins to run during jsonrpc2.bindConnection, and
can race with the setting of conn.write in bindConnection.
This PR adds a sleep, which is a poor way to deal with the race, but
the least invasive change. Better ones include running the test
function after Dial returns, or adding a Connection.Ready method
to detect when initialization is complete.
This CL introduces a fundamental change to the jsonrpc2 library:
connection writes, which were previously serialized by the jsonrpc2
library itself, are now allowed to be concurrent.
The change in semantics of the jsonrpc2 library should hopefully be easy
to review, since moving the synchronization to the Writer implementation
is equivalent to the previous logic. However, this change is critical
for the streamable client transport, because it allows for concurrent
http requests to the server.
Consider that a write is a POST to the server, and we don't know that
write succeeded until we get the response header. Previously, we had the
following problem: if the client POSTs a request, and the server blocks
its response on a request made through the hanging GET, the client was
unable to respond because the initial POST is still blocked. We could
update our streamable server transport to force a flush of the response
headers, but we can't guarantee that other servers behave the same way.
Fundamentally, writes in the spec are asynchronous, and we need to
support that.
This CL effectively removes any dependencies on mcp from jsonschema.
This will enable us to move the repo.
This CL also deletes unused marshalStructWithMap and
unmarshalStructWithMap which had a dependency on FieldJSONInfo.
Fixes: #250
Audit all cases where params must not be null, and enforce this using
methodInfo via a new methodFlags bitfield that parameterizes method
requirements. Write extensive conformance tests catching all the
(server-side) crashes that were possible.
We should go further and validate schema against the spec, but that is
more indirect, more complicated, and potentially slower. For now we
adopt this more explicit approach.
Still TODO in a subsequent CL: verify the client side of this with
client conformance tests.
Additionally, improve some error messages that were redundant or leaked
internal implementation details.
Fixes#195
This fixes#151, which makes it easier for users to easily use GitHub
Codespaces, providing them with a VS Code like environment with their
preferred settings/themes and the required dependencies, all within the
browser.
This PR improves the formatting and internal link structure of both the
main `README.md` and the source file at `internal/readme/README.src.md`.
Changes include:
### 🛠 Changes Made
* Replaced plain-text warning with a GitHub-style admonition block (`>
[!WARNING]`) for improved visibility and consistency with other docs.
Example:
> [!WARNING]
> The SDK should be considered unreleased, and is currently unstable
> and subject to breaking changes. Please test it out and file bug
reports or API
> proposals, but don't use it in real projects. See the issue tracker
for known
> issues and missing features. We aim to release a stable version of the
SDK in
> August, 2025.
* Updated markdown links to use cleaner relative paths:
* Changed `CONTRIBUTING.md` reference to
`[CONTRIBUTING.md](/CONTRIBUTING.md)`
* Updated `examples/` reference to `[examples/](/examples/)`
* Ensured that all updates were mirrored in both the generated and
source README files.
### 📌 Why It Matters
These changes improve the readability and usability of the
documentation, especially when viewed on GitHub. The updated formatting
helps call attention to important warnings, and fixing relative paths
ensures that links work reliably across platforms and contexts.
Expose `jsonrpc2.MakeID`, `jsonrpc2.EncodeMessage` and
`jsonrpc2.DecodeMessage` functions to allow implementing custom
`mcp.Transport`.
Add an example that demonstrates a custom transport
implementation.
Fixes#110.
BREAKING CHANGE
Change the API for adding tools, prompts, resources and resource
templates to a server.
The ServerXXX types are gone along with the plural Add methods
(AddTools, AddPrompts etc.)
Instead there are single Add methods (AddTool, AddPrompt).
In addition, instead of NewServerTool, there is AddTool[In, Out].
Fixes#73.
Fix an example using params.Name instead of params.Arguments.Name. All
credit due to @A11Might for noticing this. Sending a separate PR to keep
the internal/readme source consistent.
After some experience with the flattened version of Content, we see that
it can easily lead to incorrect usage and is a harder API to read.
Therefore, this CL changes back to a design similar to what we had prior
to https://go.dev/cl/672415, though opting to promote content
unmarshalling to the protocol types that use it, which leads to an
overall simpler api.
* mcp: move to 2025-06-18 schema
Add types and fields for the latest MCP schema.
The main challenge here was dealing with the presence of _meta fields
on many types, like Tool, Prompt and Resource.
- Distinguish between the _meta field of a request's params, which
includes a progress token, from the _meta field on other types,
which is simply a map.
- Redefine GetMeta to return a pointer to the map. We wanted to avoid
that, but I don't see a clean way to do so. An alternative would be
to have GetMeta return a map, and SetMeta to set it.
- Provide GetProgressToken for requests only (not notifications or other
types).
- Still to do: deal with the meta and annotation fields of ContentBlock,
which are currently duplicated for Resource and ResourceContents.
* Meta and progress token redesign
Update the README to remove the table of contents, and update the target
stability date from 'mid July' to 'August': mid July does not allow
enough time for testing.
In CL 682976, Alan Donovan correctly points out that the term in the MCP
spec is 'stdio', and therefore the correct capitalization is Stdio.
Change-Id: Ib5bbe04f1a61de886298b4d0adc13aefd6aadd9c
Reviewed-on: https://go-review.googlesource.com/c/tools/+/683075
Reviewed-by: Alan Donovan <adonovan@google.com>
Auto-Submit: Robert Findley <rfindley@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Change CONTRIBUTING.md and README.md to reflect that the MCP SDK is
being moved to github.com/modelcontextprotocol/go-sdk, and to include
content from the 'Governance' section of the design doc. Also, include
the antitrust policy as a section in CONTRIBUTING.md.
Change-Id: I46784d8e57b2a2cab8895593f633d20a2e15c8ba
Reviewed-on: https://go-review.googlesource.com/c/tools/+/682976
Reviewed-by: Sam Thanawalla <samthanawalla@google.com>
Auto-Submit: Robert Findley <rfindley@google.com>
Reviewed-by: Alan Donovan <adonovan@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Remove dependencies on the eventtest and testenv packages from
jsonrpc2_v2 and mcp packages, in preparation for forking.
Change-Id: Id0efb0c3187629f6fb1822cc853ec52acea41b0d
Reviewed-on: https://go-review.googlesource.com/c/tools/+/682696
Reviewed-by: Jonathan Amsterdam <jba@google.com>
Auto-Submit: Robert Findley <rfindley@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
The NewTool and NewPrompt constructors were unidiomatic, because they
returned a ServerTool and ServerPrompt, respectively, rather than a Tool
and Prompt. Rename to be consistent with the constructed object name.
Change-Id: Ife3f16f783368401f792660c4272e1bb5ae61638
Reviewed-on: https://go-review.googlesource.com/c/tools/+/682375
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Jonathan Amsterdam <jba@google.com>
In preparation for extracting the jsonrpc2_v2 package, update the Reader
and Writer interfaces to not report byte counts, and remove the
internal/event dependency.
Change-Id: Ie6b373736fe297c8427cd4ece7ddad33e275864b
Reviewed-on: https://go-review.googlesource.com/c/tools/+/678956
Reviewed-by: Alan Donovan <adonovan@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
CallToolParams.Arguments is any.
Clients can send whatever they want.
Tool authors who create their own ToolHandler (bypassing NewTool)
will receive the arguments as a map[string]any which has been
validated against the input schema.
Tool authors who call NewTool can choose the type that the arguments
unmarshal into.
There is no double-unmarshaling and no downcasting.
There is no way for tool authors to avoid the unmarshal, and no way to
avoid the validation unless the omit an input schema, which is probably
bad for LLMs. If tool authors want this optimization, we can provide
it later.
Change-Id: Ieb201e56c7fb8a23bb1a93b27e946630ec9e79ad
Reviewed-on: https://go-review.googlesource.com/c/tools/+/679595
TryBot-Bypass: Jonathan Amsterdam <jba@google.com>
Auto-Submit: Jonathan Amsterdam <jba@google.com>
Reviewed-by: Robert Findley <rfindley@google.com>
Add Wrapf, a function that helps with error wrapping.
Change-Id: I102695f75e4d217e09f828f4723cbfcbbe83f887
Reviewed-on: https://go-review.googlesource.com/c/tools/+/679177
Reviewed-by: Robert Findley <rfindley@google.com>
Reviewed-by: Sam Thanawalla <samthanawalla@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Do a thorough job of parsing json struct tags.
Move the code to a place where both mcp and jsonschema can use it.
Change-Id: I6c86308834706b12a1e22cd96ae120590f49d3f4
Reviewed-on: https://go-review.googlesource.com/c/tools/+/678757
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Robert Findley <rfindley@google.com>
Make Tool APIs future-proof by pushing generics into CallToolParams, and
using CallToolParams throughout. This has several advantages:
- We no longer need the awkward CallToolOptions type, which is almost
but not quite like CallToolParams.
- NewTool no longer needs to define its own handler type: it accepts a
ToolHandler[TArgs]. This also means its signature is future-proof.
Additionally, provide a `CallTool` helper (the analog of NewTool) to
serve as a more strongly typed variant of `ClientSession.CallTool`.
+ design, protocol generation
Change-Id: I80172a25bc50734dae84a541aa4776ed9161694e
Reviewed-on: https://go-review.googlesource.com/c/tools/+/676495
Reviewed-by: Jonathan Amsterdam <jba@google.com>
Auto-Submit: Robert Findley <rfindley@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Modify the conformance test driver to support outgoing responses.
They are returned for incoming requests in order.
Add a test that returns a file resource, which involves the server
sending a roots/list request to the client.
Change-Id: Ie7eb69a8c99ccbf11721518cfffb21244c03e532
Reviewed-on: https://go-review.googlesource.com/c/tools/+/677475
Commit-Queue: Jonathan Amsterdam <jba@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Robert Findley <rfindley@google.com>
Add the beginnings of some testdata-driven conformance tests that check
JSON-level compatibility of SDK messages, and fix some bugs in our JSON
message handling:
- "params" can be missing
- "_meta" should not be null
- lists of tools/prompts/resources should not be null
In order to implement this, we need to be able to know when the server
is done processing messages. In general, this is a hard problem; for
gopls we do this with a complicated system of progress reporting and
accounting. However, the new synctest package makes this trivial, as we
can call synctest.Wait to detect when the server is idle. Therefore,
this test requires 1.25 (it uses synctest.Test, added in 1.25, and so
can't run at 1.24 with GOEXPERIMENT=synctest).
Change-Id: I97fa28b56868340ece266a58e1eb3c3bf8cfe0e9
Reviewed-on: https://go-review.googlesource.com/c/tools/+/676538
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Jonathan Amsterdam <jba@google.com>
Auto-Submit: Robert Findley <rfindley@google.com>
Change-Id: I8066b22cb87e09fb160de3b8ff2d8fdde6ec3dcf
Reviewed-on: https://go-review.googlesource.com/c/tools/+/675815
Reviewed-by: David Chase <drchase@google.com>
Auto-Submit: Alan Donovan <adonovan@google.com>
Reviewed-by: Alan Donovan <adonovan@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Use the weave program from golang.org/x/example to weave together
the README text with buildable programs. This ensures the code in the
README compiles.
Change-Id: Ib5e10c8f808cc6d1ed4addbee784607e910ba30b
Reviewed-on: https://go-review.googlesource.com/c/tools/+/673796
Reviewed-by: Robert Findley <rfindley@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Now that the protocol package is merged into the mcp package, clean up
the higher level 'Content' union types, in favor of types constructors.
Change-Id: I37bedb0ff0a296eef799ba65c37ca7f94ee1dbbe
Reviewed-on: https://go-review.googlesource.com/c/tools/+/672415
Reviewed-by: Jonathan Amsterdam <jba@google.com>
TryBot-Bypass: Jonathan Amsterdam <jba@google.com>
The generated protocol package is part of the SDK API, so it shouldn't
be internal.
Change-Id: I5306af48019b1599707b939b348eb6ae4f766ca9
Reviewed-on: https://go-review.googlesource.com/c/tools/+/670356
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Jonathan Amsterdam <jba@google.com>
