fix: resolve MCP bridge timeout on slow LLM endpoints (#1769)#1772
Closed
zhu6201976 wants to merge 1 commit intounclecode:mainfrom
Closed
fix: resolve MCP bridge timeout on slow LLM endpoints (#1769)#1772zhu6201976 wants to merge 1 commit intounclecode:mainfrom
zhu6201976 wants to merge 1 commit intounclecode:mainfrom
Conversation
Owner
|
Thanks for taking the time to contribute this fix! Your work helped identify and solve this issue - the fix was implemented on the develop branch (via a different approach) and will be in the next release. We've added you to our CONTRIBUTORS file in recognition of your effort. Closing this PR as the fix is already on develop. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem:
The current mcp_bridge uses httpx.AsyncClient with its default 5-second timeout. When interfacing with LLM-backed endpoints (especially complex reasoning tasks or slow TTFT), this frequently triggers a TimeoutException, resulting in an isError response even when the backend is functioning correctly.
Solution:
Increased the httpx timeout to 300 seconds (5 minutes) to accommodate typical LLM processing times.
Implemented a structured httpx.Timeout(300.0, connect=10.0) for better connection management.
Added explicit error handling for httpx.TimeoutException to provide clearer feedback to the user.
Impact:
Improved stability for MCP-based workflows, particularly when using agents or slow upstream LLM APIs.
How to test:
Set up an MCP bridge pointing to a mock endpoint with a >5s delay.
Verified that the request now completes successfully instead of timing out at 5s.
Verified that requests exceeding 300s return the new descriptive error message.