modelcontextprotocol / modelcontextprotocol/servers

Requested timeout

Open
#719 2 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
TypeScript
Stars
90.5k
Forks
11.7k
Avg merge
2d 2h
Merged PRs (30d)
5

Description

Describe the bug
Hi, I encountered some error when running my own mcp server.
I tried to install my own image inference structure to my computer (using macos, and mps for inference), after I installed the dependencies as required, the log of my server just warned me 32001 Error.

Logs

2025-03-03T02:11:56.989Z [screenparser] [info] Initializing server...
2025-03-03T02:11:56.993Z [screenparser] [info] Server started and connected successfully
2025-03-03T02:11:57.036Z [screenparser] [info] Message from client: {"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"claude-ai","version":"0.1.0"}},"jsonrpc":"2.0","id":0}
Downloading scipy (21.3MiB)
Downloading easyocr (2.7MiB)
Downloading scikit-learn (10.6MiB)
Downloading opencv-python-headless (35.6MiB)
Downloading numpy (13.3MiB)
Downloading opencv-contrib-python (44.1MiB)
Downloading torchvision (1.7MiB)
Downloading shapely (1.3MiB)
Downloading cython (1.1MiB)
Downloading scikit-image (12.6MiB)
Downloading lxml (7.8MiB)
Downloading rapidfuzz (1.4MiB)
Downloading rapidfuzz (1.4MiB)
 Downloaded cython
 Downloaded shapely
 Downloaded rapidfuzz
 Downloaded torchvision
 Downloaded cython
 Downloaded shapely
 Downloaded easyocr
 Downloaded rapidfuzz
 Downloaded torchvision
 Downloaded easyocr
 Downloaded lxml
 Downloaded scikit-learn
 Downloaded lxml
 Downloaded scikit-image
 Downloaded numpy
2025-03-03T02:12:55.939Z [screenparser] [info] Message from client: {"jsonrpc":"2.0","method":"notifications/cancelled","params":{"requestId":0,"reason":"Error: MCP error -32001: Request timed out"}}
2025-03-03T02:12:55.940Z [screenparser] [info] Client transport closed
2025-03-03T02:12:55.941Z [screenparser] [info] Server transport closed
2025-03-03T02:12:55.941Z [screenparser] [info] Client transport closed
2025-03-03T02:12:55.941Z [screenparser] [info] Server transport closed unexpectedly, this is likely due to the process exiting early. If you are developing this MCP server you can add output to stderr (i.e. `console.error('...')` in JavaScript, `print('...', file=sys.stderr)` in python) and it will appear in this log.
2025-03-03T02:12:55.941Z [screenparser] [error] Server disconnected. For troubleshooting guidance, please visit our [debugging documentation](https://modelcontextprotocol.io/docs/tools/debugging) {"context":"connection"}
2025-03-03T02:12:55.950Z [screenparser] [info] Server transport closed
2025-03-03T02:12:55.950Z [screenparser] [info] Client transport closed
2025-03-03T02:12:57.034Z [screenparser] [info] Message from client: {"jsonrpc":"2.0","method":"notifications/cancelled","params":{"requestId":0,"reason":"Error: MCP error -32001: Request timed out"}}
2025-03-03T02:12:57.035Z [screenparser] [info] Client transport closed
2025-03-03T02:12:57.036Z [screenparser] [info] Server transport closed
2025-03-03T02:12:57.036Z [screenparser] [info] Client transport closed
2025-03-03T02:12:57.036Z [screenparser] [info] Server transport closed unexpectedly, this is likely due to the process exiting early. If you are developing this MCP server you can add output to stderr (i.e. `console.error('...')` in JavaScript, `print('...', file=sys.stderr)` in python) and it will appear in this log.
2025-03-03T02:12:57.036Z [screenparser] [error] Server disconnected. For troubleshooting guidance, please visit our [debugging documentation](https://modelcontextprotocol.io/docs/tools/debugging) {"context":"connection"}
2025-03-03T02:12:57.043Z [screenparser] [info] Server transport closed
2025-03-03T02:12:57.044Z [screenparser] [info] Client transport closed

Additional context
I am thinking this is due to the dependencies, but the error information from the log is not sufficient.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the MCP server startup on macOS with MPS and inspect the dependency downloads alongside the initialization and cancellation logs. Done means determining whether dependency installation or startup exceeds the client timeout, then documenting or fixing the identified cause.

Written by the indexing model from the issue text.

Assessment

Tech stack
macos, opencv, python
Domain
api, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.