ClosedResourceError During MCP Stateless Server Shutdown When Sending Log Messages

[jonfinerty]

Initial Checks

• I confirm that I'm using the latest version of MCP Python SDK
• I confirm that I searched for my issue in https://github.com/modelcontextprotocol/python-sdk/issues before opening this issue

Description

I'm seeing occasional errors from our MCP server, which I think are a race condition during shutdown.

I think this is a similar but distinct issue to the race condition in #1190 and #1384 as this is during send_log_message

I haven't been able to get a consistent reproduce yet, will update when I can.

Stack Trace

+ Exception Group Traceback (most recent call last):
 | File "/app/.venv/lib/python3.13/site-packages/mcp/server/streamable_http_manager.py", line 180, in run_stateless_server
 | await self.app.run(
 | ...<4 lines>...
 | )
 | File "/app/.venv/lib/python3.13/site-packages/fastmcp/server/low_level.py", line 202, in run
 | async with AsyncExitStack() as stack:
 | ~~~~~~~~~~~~~~^^
 | File "/usr/local/lib/python3.13/contextlib.py", line 768, in __aexit__
 | raise exc
 | File "/usr/local/lib/python3.13/contextlib.py", line 751, in __aexit__
 | cb_suppress = await cb(*exc_details)
 | ^^^^^^^^^^^^^^^^^^^^^^
 | File "/app/.venv/lib/python3.13/site-packages/mcp/shared/session.py", line 238, in __aexit__
 | return await self._task_group.__aexit__(exc_type, exc_val, exc_tb)
 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 | File "/app/.venv/lib/python3.13/site-packages/anyio/_backends/_asyncio.py", line 783, in __aexit__
 | raise BaseExceptionGroup(
 | "unhandled errors in a TaskGroup", self._exceptions
 | ) from None
 | ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
 +-+---------------- 1 ----------------
 | Exception Group Traceback (most recent call last):
 | File "/app/.venv/lib/python3.13/site-packages/fastmcp/server/low_level.py", line 214, in run
 | async with anyio.create_task_group() as tg:
 | ~~~~~~~~~~~~~~~~~~~~~~~^^
 | File "/app/.venv/lib/python3.13/site-packages/anyio/_backends/_asyncio.py", line 783, in __aexit__
 | raise BaseExceptionGroup(
 | "unhandled errors in a TaskGroup", self._exceptions
 | ) from None
 | ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
 +-+---------------- 1 ----------------
 | Traceback (most recent call last):
 | File "/app/.venv/lib/python3.13/site-packages/mcp/server/lowlevel/server.py", line 694, in _handle_message
 | await session.send_log_message(
 | ...<3 lines>...
 | )
 | File "/app/.venv/lib/python3.13/site-packages/mcp/server/session.py", line 213, in send_log_message
 | await self.send_notification(
 | ...<10 lines>...
 | )
 | File "/app/.venv/lib/python3.13/site-packages/mcp/shared/session.py", line 335, in send_notification
 | await self._write_stream.send(session_message)
 | File "/app/.venv/lib/python3.13/site-packages/anyio/streams/memory.py", line 249, in send
 | self.send_nowait(item)
 | ~~~~~~~~~~~~~~~~^^^^^^
 | File "/app/.venv/lib/python3.13/site-packages/anyio/streams/memory.py", line 218, in send_nowait
 | raise ClosedResourceError
 | anyio.ClosedResourceError
 +------------------------------------

Python & MCP Python SDK

MCP SDK Version: 1.25.0
via fastmcp Version: 2.14.4
Python Version: 3.13.5

[maxisbey]

Could you please provide a minimal reproducible example code snippet we can run to get the error?

[felixweinberger]

thanks for the detailed stack trace. this does look like a distinct race from #1384 — the write stream is getting closed before the log notification can be sent.

can you share a minimal reproduction when you get one? ideally a small script we can run to trigger the shutdown race. info about your transport setup (streamable HTTP?) and what's triggering the log messages during shutdown would help too.

[tokoyoda]

I hit what appears to be the same ClosedResourceError on mcp 1.26.0 with streamable-http transport (stateful mode). The crash occurs reliably whenever the MCP client disconnects while a long-running tool handler is still in progress. Below is a minimal reproduction and root cause analysis.

Reproduction

#!/usr/bin/env python3
# /// script
# requires-python = "==3.14.*"
# dependencies = ["mcp==1.26.0", "httpx==0.28.1"]
# ///
"""
Reproduce ClosedResourceError when DELETE is sent during in-flight tool handler.

 uv run reproduce_minimal.py

https://github.com/modelcontextprotocol/python-sdk/issues/1967
"""

import asyncio
import httpx
from mcp.server import FastMCP

# ---------- Server ----------

server = FastMCP("repro-server", host="localhost", port=9999)


@server.tool(description="Simulates a long-running operation")
async def slow_task(seconds: float = 3.0) -> dict:
 print(f"[server] slow_task: sleeping {seconds}s ...")
 await asyncio.sleep(seconds)
 print("[server] slow_task: done, sending response ...")
 return {"ok": True}


# ---------- Client ----------

BASE = "http://localhost:9999/mcp"
H = {"Accept": "application/json, text/event-stream", "Content-Type": "application/json"}


async def run_client():
 """Init session -> call slow_task -> DELETE mid-flight -> observe crash."""
 await asyncio.sleep(2) # wait for server startup

 async with httpx.AsyncClient(timeout=30) as c:
 # 1. Initialize
 r = await c.post(BASE, json={
 "jsonrpc": "2.0", "id": 1, "method": "initialize",
 "params": {
 "protocolVersion": "2024-11-05",
 "capabilities": {},
 "clientInfo": {"name": "repro", "version": "0.1"},
 },
 }, headers=H)
 sid = r.headers["mcp-session-id"]
 print(f"[client] session: {sid[:12]}...")
 sh = {**H, "mcp-session-id": sid}

 # 2. Initialized notification
 await c.post(BASE, json={"jsonrpc": "2.0", "method": "notifications/initialized"}, headers=sh)

 # 3. Call slow_task (fire-and-forget with short timeout)
 async def call_slow():
 async with httpx.AsyncClient(timeout=httpx.Timeout(1.0)) as c:
 try:
 await c.post(BASE, json={
 "jsonrpc": "2.0", "id": 2, "method": "tools/call",
 "params": {"name": "slow_task", "arguments": {"seconds": 3}},
 }, headers=sh)
 except httpx.ReadTimeout:
 pass # expected

 asyncio.create_task(call_slow())
 await asyncio.sleep(1) # let task start on server

 # 4. DELETE -> terminate session while slow_task is still running
 print("[client] sending DELETE to terminate session mid-task ...")
 async with httpx.AsyncClient(timeout=5) as c:
 r = await c.delete(BASE, headers=sh)
 print(f"[client] DELETE response: {r.status_code}")

 # 5. Wait for server to hit the error
 print("[client] waiting for slow_task to finish on server ...")
 await asyncio.sleep(3)
 print("[client] done")


# ---------- Main ----------

async def main():
 import threading
 t = threading.Thread(target=lambda: server.run(transport="streamable-http"), daemon=True)
 t.start()
 await run_client()

asyncio.run(main())

Root Cause

terminate() closes _write_stream immediately without waiting for in-flight handlers. When a handler finishes and calls respond() → _send_response() → _write_stream.send(), it raises ClosedResourceError which propagates unhandled through the TaskGroup, crashing the session.

1. Client sends DELETE → _handle_delete_request → terminate() closes all streams
2. _receive_loop() exits its async with block → _write_stream closed
3. Server.run() TaskGroup waits for in-flight handlers
4. Handler calls message.respond() → _send_response() → _write_stream.send() → ClosedResourceError

The existing ClosedResourceError catch in _receive_loop only guards the read side, not the write path used by handlers.

Note: streamablehttp_client defaults to terminate_on_close=True, so every normal client disconnect sends DELETE — meaning any long-running tool handler will crash the session.