Skip to content

fix: resolve MCP bridge timeout on slow LLM endpoints (#1769)#1772

Open
zhu6201976 wants to merge 1 commit intounclecode:mainfrom
zhu6201976:fix/1769-mcp-bridge-timeout
Open

fix: resolve MCP bridge timeout on slow LLM endpoints (#1769)#1772
zhu6201976 wants to merge 1 commit intounclecode:mainfrom
zhu6201976:fix/1769-mcp-bridge-timeout

Conversation

@zhu6201976
Copy link

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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant