Fetch MCP server fails with -32000 Connection Closed on LM Studio #2517
Description
Describe the bug
The Fetch MCP server randomly fails to run (often second use, sometimes third use):
To Reproduce
Steps to reproduce the behavior:
- Install LM Studio
- add the Fetch MCP server to its
mcp.jsonusing the docker version:
"fetch": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"mcp/fetch"
]
}- reload the tool until it fails:
You may also load a model and prompt it with a link, but the response generation stops immediately.
Expected behavior
It should properly reload the tools when requested.
Prompting should not fail.
Logs
2025-08-09 17:37:14 [INFO]
[Plugin(mcp/fetch)] stdout: [Tools Prvdr.] Register with LM Studio
2025-08-09 17:37:15 [INFO]
[Plugin(mcp/fetch)] stdout: [Tools Prvdr.] Register with LM Studio
2025-08-09 17:37:19 [INFO]
[Plugin(mcp/fetch)] stdout: [Tools Prvdr.] Register with LM Studio
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: + Exception Group Traceback (most recent call last):
| File "/app/.venv/lib/python3.11/site-packages/mcp/server/stdio.py", line 83, in stdio_server
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | yield read_stream, write_stream
| File "/app/.venv/lib/python3.11/site-packages/mcp_server_fetch/server.py", line 288, in serve
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | await server.run(read_stream, write_stream, options, raise_exceptions=True)
| File "/app/.venv/lib/python3.11/site-packages/mcp/server/lowlevel/server.py", line 424, in run
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | async with ServerSession(
| File "/app/.venv/lib/python3.11/site-packages/mcp/shared/session.py", line 122, in __aexit__
| return await self._task_group.__aexit__(exc_type, exc_val, exc_tb)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/app/.venv/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 763, in __aexit__
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | raise BaseExceptionGroup(
| ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/app/.venv/lib/python3.11/site-packages/mcp/shared/session.py", line 235, in _receive_loop
| notification = self._receive_notification_type.model_validate(
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/app/.venv/lib/python3.11/site-packages/pydantic/main.py", line 627, in model_validate
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | return cls.__pydantic_validator__.validate_python(
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | pydantic_core._pydantic_core.ValidationError: 5 validation errors for ClientNotification
ProgressNotification.method
Input should be 'notifications/progress' [type=literal_error, input_value='notifications/cancelled', input_type=str]
For further information visit https://errors.pydantic.dev/2.10/v/literal_error
ProgressNotification.params.progressToken
Field required [type=missing, input_value={'requestId': 1, 'reason'... operation was aborted'}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.10/v/missing
ProgressNotification.params.progress
Field required [type=missing, input_value={'requestId': 1, 'reason'... operation was aborted'}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.10/v/missing
InitializedNotification.method
Input should be 'notifications/initialized' [type=literal_error, input_value='notifications/cancelled', input_type=str]
For further information visit https://errors.pydantic.dev/2.10/v/literal_error
RootsListChangedNotification.method
Input should be 'notifications/roots/list_changed' [type=literal_error, input_value='notifications/cancelled', input_type=str]
For further information visit https://errors.pydantic.dev/2.10/v/literal_error
+------------------------------------
During handling of the above exception, another exception occurred:
+ Exception Group Traceback (most recent call last):
| File "/app/.venv/bin/mcp-server-fetch", line 10, in <module>
| sys.exit(main())
| ^^^^^^
| File "/app/.venv/lib/python3.11/site-packages/mcp_server_fetch/__init__.py", line 21, in main
| asyncio.run(serve(args.user_agent, args.ignore_robots_txt, args.proxy_url))
| File "/root/.local/share/uv/python/cpython-3.11.13-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 190, in run
| return runner.run(main)
| ^^^^^^^^^^^^^^^^
| File "/root/.local/share/uv/python/cpython-3.11.13-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 118, in run
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | return self._loop.run_until_complete(task)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/root/.local/share/uv/python/cpython-3.11.13-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 654, in run_until_complete
| return future.result()
| ^^^^^^^^^^^^^^^
| File "/app/.venv/lib/python3.11/site-packages/mcp_server_fetch/server.py", line 287, in serve
| async with stdio_server() as (read_stream, write_stream):
| File "/root/.local/share/uv/python/cpython-3.11.13-linux-x86_64-gnu/lib/python3.11/contextlib.py", line 231, in __aexit__
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | await self.gen.athrow(typ, value, traceback)
| File "/app/.venv/lib/python3.11/site-packages/mcp/server/stdio.py", line 80, in stdio_server
| async with anyio.create_task_group() as tg:
| File "/app/.venv/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 763, in __aexit__
| raise BaseExceptionGroup(
| ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Exception Group Traceback (most recent call last):
| File "/app/.venv/lib/python3.11/site-packages/mcp/server/stdio.py", line 83, in stdio_server
| yield read_stream, write_stream
| File "/app/.venv/lib/python3.11/site-packages/mcp_server_fetch/server.py", line 288, in serve
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | await server.run(read_stream, write_stream, options, raise_exceptions=True)
| File "/app/.venv/lib/python3.11/site-packages/mcp/server/lowlevel/server.py", line 424, in run
| async with ServerSession(
| File "/app/.venv/lib/python3.11/site-packages/mcp/shared/session.py", line 122, in __aexit__
| return await self._task_group.__aexit__(exc_type, exc_val, exc_tb)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/app/.venv/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 763, in __aexit__
2025-08-09 17:37:22 [ERROR]
[Plugin(mcp/fetch)] stderr: | raise BaseExceptionGroup(
| ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/app/.venv/lib/python3.11/site-packages/mcp/shared/session.py", line 235, in _receive_loop
| notification = self._receive_notification_type.model_validate(
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/app/.venv/lib/python3.11/site-packages/pydantic/main.py", line 627, in model_validate
| return cls.__pydantic_validator__.validate_python(
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| pydantic_core._pydantic_core.ValidationError: 5 validation errors for ClientNotification
ProgressNotification.method
Input should be 'notifications/progress' [type=literal_error, input_value='notifications/cancelled', input_type=str]
For further information visit https://errors.pydantic.dev/2.10/v/literal_error
ProgressNotification.params.progressToken
Field required [type=missing, input_value={'requestId': 1, 'reason'... operation was aborted'}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.10/v/missing
ProgressNotification.params.progress
Field required [type=missing, input_value={'requestId': 1, 'reason'... operation was aborted'}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.10/v/missing
InitializedNotification.method
Input should be 'notifications/initialized' [type=literal_error, input_value='notifications/cancelled', input_type=str]
For further information visit https://errors.pydantic.dev/2.10/v/literal_error
RootsListChangedNotification.method
Input should be 'notifications/roots/list_changed' [type=literal_error, input_value='notifications/cancelled', input_type=str]
For further information visit https://errors.pydantic.dev/2.10/v/literal_error
+------------------------------------
Additional context
No problem with MCP server file system, so seems to be specific to fetch.
I use Fedora 42, but it should not be relevant since I use the docker version.