You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on Nov 12, 2026. It is now read-only.
Repository navigation
This repository was archived by the owner on Nov 12, 2026. It is now read-only.
Hey, i am trying to run https://github.com/u14app/deep-research with metamcp (worked with mcpo). The mcp server is connected properly and the tools are found and i can use them through the metamcp inspector. But everytime i try to run the deep-research tool after some time i get hit with this error message https://github.com/u14app/deep-research although i an see, that the mcp server is still running and doing its stuff. It doesnt change either using sse or streamable-http.
I also tried setting both timeout values to 3000000 ms (which seems to be the highest value possible), after about 5-10 minutes the error message appears.
Edit: Also noticed this seems to happen, when there was a fetch error from the mcp server.
The deep-research container (or searxng, not sure) has a problem/error, but the overall research task continues, but metamcp seems to interpret this as an error and interupts the whole tool call.
So how long will this tool run, I am happy to increase the max request timeout but typically I don't think that's a good pattern as the connection itself may be broken if it is too long.
So how long will this tool run, I am happy to increase the max request timeout but typically I don't think that's a good pattern as the connection itself may be broken if it is too long.
Hm, thats a good question. As its a deep-research tool that is fetching a lot of data online it will take quite a while. In my few tests i saw runs of over an hour or more
Activity
zhjch05 commentedon Sep 7, 2025
So how long will this tool run, I am happy to increase the max request timeout but typically I don't think that's a good pattern as the connection itself may be broken if it is too long.
Joly0 commentedon Sep 7, 2025
Hm, thats a good question. As its a deep-research tool that is fetching a lot of data online it will take quite a while. In my few tests i saw runs of over an hour or more
Stavitsky commentedon Sep 8, 2025
Hey 👋
I have a similar question, though I’m not sure it’s exactly the same issue (if it turns out unrelated, I’ll open a separate issue).
I suspect this might be related to the bug described in modelcontextprotocol/typescript-sdk#245.
zhjch05 commentedon Sep 10, 2025
Update will increase timeout to 24hrs in next version (not shipped yet) https://github.com/metatool-ai/metamcp/tree/2.4.15
Joly0 commentedon Sep 25, 2025
Btw, this is still an issue even with the latest version. The metamcp logs show this error:
When this happens, the mcp server (deep-research) logs throw this error:
but continues working without problems
jsapede commentedon Feb 11, 2026
is there news on this error ?
got it also MCP error -32001: Request timed out
medram commentedon Aug 23, 2026
Having the same issue:
MCP error -32001: Request timed out
Any solution guys?
feat(oauth): refresh-token family reuse detection, iss on the legacy …
docs(fork): log metatool-ai#155 in the divergence ledger (metatool-ai…
build(deps): clear the 2026-10-08 security alerts with minimal bumps (m…