Handle Abrupt Server Disconnect in Middle of Tool Call

[EiffL]

Propagates transport disconnects (e.g. server killed mid tool call) as CONNECTION_CLOSED errors instead of hanging indefinitely. Adds regression test.

Motivation and Context

A call_tool over the StreamableHTTP transport would hang forever if the server closed the SSE/HTTP connection mid-response (e.g. process crash/kill). The underlying RemoteProtocolError was logged but in‑flight requests never completed. This change converts that low-level failure into a deterministic JSON-RPC error for every pending request, matching expected resilience semantics.

How Has This Been Tested?

• Added integrated test test_streamable_http_mid_call_disconnect:
  • Starts real server process.
  • Invokes long-running tool (wait_for_lock_with_notification).
  • Kills server mid-call.
  • Asserts an McpError with code CONNECTION_CLOSED (previously would hang).
• All existing tests pass locally.

Breaking Changes

None. Behavior only changes for abnormal transport termination; normal flows unaffected. No public API changes.

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update

Checklist

• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed

Additional context

Implementation details:

In _handle_sse_response (client transport) on exception: send the exception into the session read stream then close the writer to signal termination.

In BaseSession._receive_loop: on receiving an Exception, broadcast a synthesized JSONRPCError (code CONNECTION_CLOSED) to all pending request streams and clear them.

Integrated test placed alongside existing StreamableHTTP tests for consistency. Potential follow-up: introduce optional reconnection/resumption logic for recoverable disconnects.