This CL implements two changes that must be logically connected.
The first is to provide a mechanism for disabling stream replay.
Previously, our documentation stated that if
StreamableServerTransport.EventStore was nil, a default in-memory event
store would be used. In that case, there would be no way to completely
disable stream replay, and as described in #576, there are many cases
where replay is undesirable.
But of course changing the behavior of the transport zero value
implicitly affects its default behavior, and so this CL also implements
the proposal #580: stream replay is disabled by default.
Implementing this change required a significant refactoring, as
previously we were relying on the event store for serialized message
delivery from the JSON-RPC layer to the MCP layer: the connection would
write to the event store, and independently the stream (be it an
incoming POST or replay GET) would iterate and serve messages in the
stream.
In order to achieve the goals of this CL, it was necessary to decouple
storage from delivery. The 'stream' abstraction now tracks a delivery
callback that writes straight to the HTTP response. It would have been
convenient to store the ongoing http.ResponseWriter directly in the
stream (this is how typescript does it), but due to the design of our
EventStore API, only the HTTP handler knows the next event index, so a
'deliver' abstraction was an unfortunate requirement (suggestions for
how to further simplify this are welcome).
More simplification is possible: in particular, as a result of this
refactoring it should be entirely possible to clean up streams once
we've received all responses. Any replay would only need access to the
EventStore, if at all. This is left to a follow-up CL, to limit this
already significant change.
Furthermore, a nice consequence of this refactoring is that, when not
using event storage, servers can get synchronous feedback that message
delivery failed, which should avoid unnecessary work. We can
additionally cancel ongoing requests on early client termination, but
that is also left to a follow-up CL.
Throughout, the terminology 'standalone SSE stream' replaced 'hanging
GET' when referring to the non-replay GET request issued by the client.
This is consistent with other SDKs.
Fixes#576
Updates #580
This PR fixes goroutine leaks in all unit tests.
To find the leaks I integrated https://github.com/uber-go/goleak and I
suggest to keep using it to catch any future regressions.
I used the folowing script to more easily find individual tests which
were leaking goroutines:
```
for t in $(go test -run=Nothing -list=. ./mcp | grep -v ok); do go test ./mcp -run="$t" > /dev/null && echo -n . || echo -e "\nDetected leak: $t"; done
```
PR 501 added logging to the streamable server, but didn't pass a non-nil
logger to the streamable transport (an oversight). However, tests still
passed due to net/http's panic recovery.
Update test servers to enforce that handlers do not panic, and fix the
panic by:
1. Passing along the configured logger to the session transport.
2. Using ensureLogger in Connect, since we technically allow
StreamableServerTransports to be constructed by the user.
Fixes#556
## Problem
Context propagation was broken in `StreamableClientTransport` because:
1. `Connect()` used `context.Background()` instead of the parent context
2. `Close()` created a race condition where DELETE requests were
cancelled before completion
## Solution
- Use parent context when creating the connection context in `Connect()`
- Reorder `Close()` operations to perform cleanup DELETE before
cancelling context
## Impact
- Request-scoped values (auth tokens, trace IDs) now propagate correctly
to background HTTP operations
- Eliminates race condition in cleanup operations
- Maintains proper Go context semantics
Fixes#513
Provide a way for middleware to get the error from a tool call,
demonstrating that we can add this functionality without making a
breaking change.
Leave getError unexported for now; we can export it (and setError) at
any time.
For #64.
Our validation logic was avoiding double-unmarshalling as much as
possible, by parsing before validation and validating the Go type.
This only works if the Go type has the same structure as its JSON
representation, which may not be the case in the presence of types with
custom MarshalJSON or UnmarshalJSON methods (such as time.Time).
But even if the Go type doesn't use any custom marshalling, validation
is broken, because we can't differentiate zero values from missing
values.
Bite the bullet and use double-unmarshalling for both input and output
schemas. Coincidentally, this fixes three bugs:
- We were accepting case-insensitive JSON keys, since we parsed first,
even though they should have been rejected. A number of tests were
wrong.
- Defaults were overriding present-yet-zero values, as noted in an
incorrect test case.
- When "arguments" was missing, validation wasn't performed, no defaults
were applied, and unmarshalling failed even if all properties were
optional.
First unmarshalling to map[string]any allows us to fix all these bugs.
Unfortunately, it means a 3x increase in the number of reflection
operations (we need to unmarshal, apply defaults and validate,
re-marshal with the defaults, and then unmarshal into the Go type).
However, this is not likely to be a significant overhead, and we can
always optimize in the future.
Update github.com/google/jsonschema-go to pick up necessary improvements
supporting this change.
Additionally, fix the error codes for invalid tool parameters, to be
consistent with other SDKs (Invalid Params: -32602).
Fixes#447Fixes#449
Updates #450
Previously, the error message received from ClientSession.Wait would
only report the closeErr, which would often be nil even if the client
transport was broken. Wait should return the reason the session
terminated, if abnormal.
I'm not sure of the exact semantics of this, but surely returning nil is
less useful than returning a meaningful non-nil error. We can refine our
handling of errors once we have more feedback.
Also add a test for client termination on HTTP server shutdown,
described in #265. This should work as long as (1) the session is
stateful (with a hanging GET), or (2) the session is stateless but the
client has a keepalive ping.
Also: don't send DELETE if the session was terminated with 404; +test.
Fixes#265
In #272, we made transports open structs and deprecated their
constructors. However, we left the constructors in place to allow go:fix
directives to facilitate migration.
Now let's remove the constructors before cutting the release.
Fixes#305
Use a fake streamable server to facilitate testing client behavior.
For this commit, just update the existing test (moved to a new file for
isolation). Subsequent CLs will add more tests.
Improve one client error message that occurred while debuging tests.
For #393
The condition sessionID == "" was not quite right for disallowing GET
requests. Since we decided to differentiate "stateless" vs "sessionless"
servers, we need to disallow GET requests for both.
For #393
Exporting StreamableHTTPOptions.JSONResponse is helpful for some users behind proxies that don't work well with text/event-stream.
For #211
Co-authored-by: ccpro10 <co1797249167@gmail.com>
An onClose function is passed to the ServerSession and ClientSession to
help cleanup resources from the caller.
The onClose function will be executed as part of the ServerSession and
ClientSession closure.
Fixes#258
The spec makes it clear that input schemas must have type "object".
Enforce that.
Allow "any" as an input argument type by special-casing it.
Fixes#283.
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.
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
Export ServerCapabilities and related subtypes and update protocol,
server, and tests to use exported types. Add InitializeResult method on
ClientSession for accessing the initialize result from sessions.
Fixes: https://github.com/modelcontextprotocol/go-sdk/issues/166
Co-authored-by: Shashank Pachava <spachava753@gmail.com>
Do a pass through the streamable client reconnection logic, and fix
several bugs.
- Establish the initial GET even if MaxRetries is 0 (#256). This was
broken because the GET bypasses the initial request and going straight
to the SSE GET reconnection logic.
- Release the stream ownership when POST requests exit.
- Don't reconnect POST requests if we've received the expected response.
- Move unexported reconnection config to constants. Otherwise it is too
hard to set ReconnectOptions (you have to use the DefaultOptions and
mutate).
Fixes#256
In #202, I added the checkRequest helper to validate incoming requests,
and invoked it in the stremable transports to preemptively reject
invalid HTTP requests, so that a jsonrpc error could be translated to an
HTTP error.
However, this introduced a bug: since cancellation was handled in the
jsonrpc2 layer, we never had to validate it in the mcp layer, and
therefore never added methodInfo. As a result, it was reported as an
invalid request in the http layer.
Add a test, and a fix. The simplest fix was to create stubs that are
placeholders for cancellation.
This was discovered in the course of investigating #285.
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
Add a new (currently unexported) jsonResponse option to
StreamableServerTransportOptions, and use it to control the response
content type, serving application/json if set.
Additionally:
- A transportOptions field is added to the StreamableHTTPOptions.
- A messages iterator is added to encapsulate the iteration of stream
messages, since the handling of JSON and SSE responses are otherwise
very different.
- The serving flow is refactored to avoid returning (statusCode,
message), primarily because this seemed liable to lead to redundant
calls to WriteHeader, because only local logic knows whether or not
any data has been written to the response.
- The serving flow is refactored to delegate to responseJSON and
responseSSE, according to the currently unexported jsonResponse
option.
- A bug is fixed where all GET streams were considered persistent: the
terminal condition req.Method == http.MethodPost && nOutstanding == 0
was not right: GET requests may implement stream resumption.
Updates #211
Make several cleanups of the streamable client transport, encountered
during work on JSON support for the streamable server:
- The 'Close' condition is differentiated from asynchronous failures. A
failure should unblock Read with an error, at which point the JSON-RPC
connection will be broken and closed.
- Fields are reordered in streamableClientConn to make guards more
apparent.
- The handling of sessionID is simplified: we simply set the session ID
whenever we receive response headers. No need to have special handling
for the first request, as the serializeation of session initialization
is implemented in Client.Connect.
- Since the above bullet makes Write a trivial wrapper around
postMessage, the two methods are merged.
- A bug is fixed where JSON responses were handled synchronously in
Write. This lead to deadlock when a hanging client->server request is
waiting on a server->client request. Now JSON is handled symmetrically
to SSE: the Write returns once response headers are received.
asynchronous to Write.
- The httpConnection interface is renamed to clientConnection, and
receive the entire InitializeResult.
- streamableClientConn receivers are renamed to be consistently 'c'.
