[BUG] Claude code does not obey values of MCP_TIMEOUT longer than 60 seconds

[marcindulak]

Preflight Checklist

• I have searched existing issues and this hasn't been reported yet
• This is a single bug report (please file separate reports for different bugs)
• I am using the latest version of Claude Code

What's Wrong?

Claude code does not obey values of MCP_TIMEOUT longer than 60 seconds

What Should Happen?

Claude code should obey longer values of MCP_TIMEOUT. This is needed for MCP servers that have a long startup times, e.g. download some resources.

Error Messages/Logs

[DEBUG] MCP server "sleep": Starting connection with timeout of 100000ms
[DEBUG] MCP server "sleep": Connection failed after 60031ms: MCP error -32001: Request timed out

Steps to Reproduce

rm -rf /tmp/claude-60seconds-timeout
mkdir /tmp/claude-60seconds-timeout
cd /tmp/claude-60seconds-timeout

export MCP_TIMEOUT=100000 # 100 seconds
claude mcp remove sleep || true
claude mcp add sleep -- bash -c "sleep infinity"

claude mcp list --debug

Output:

grep -E 'timeout|sleep' ~/.claude/debug/54bfa90c-4134-48e4-a4d3-81368ead51f8.txt 
2026-01-08T10:50:33.576Z [DEBUG] MCP server "stt-mcp-server-linux": Starting connection with timeout of 100000ms
2026-01-08T10:50:33.583Z [DEBUG] MCP server "sleep": Starting connection with timeout of 100000ms
2026-01-08T10:51:33.602Z [DEBUG] MCP server "sleep": Connection failed after 60021ms: MCP error -32001: Request timed out
2026-01-08T10:51:33.603Z [ERROR] MCP server "sleep" Connection failed: MCP error -32001: Request timed out

Claude Model

Not sure / Multiple models

Is this a regression?

No, this never worked

Last Working Version

No response

Claude Code Version

2.1.1

Platform

Anthropic API

Operating System

Ubuntu/Debian Linux

Terminal/Shell

Other

Additional Information

This is a new instance of the #7575 issue, which was incorectly closed with "60 days of inactivity", despite human comments being present. This behavior of the autoclose bot is reported in #16497.

[github-actions]

Found 2 possible duplicate issues:

1. [BUG] Claude code does not obey values of MCP_TIMEOUT longer than 60 seconds #7575
2. [BUG] MCP Timeout needs to be configurable #424

This issue will be automatically closed as a duplicate in 3 days.

• If your issue is a duplicate, please close it and 👍 the existing issue instead
• To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

[Peter4daggai]

I think mine #17662 got marked as a duplicate.
I thought this was an Anthropic API server issues (and their support even told me that they limited the tool call time to 1 minute due to "incidents")
But purely by accident i ran it on v2.0.32 and there my long running mcp tools work perfectly

[marcindulak]

The original issue described here is about a local stdio MCP server (linux sleep infinity command, not an http MCP server).

@Peter4daggai - please don't upvote the "Found possible duplicate issues:" bot like in #16837 (comment) or #17662 (comment), because by upvoting you indicate the issue is a duplicate, and the bot should close it. You need to downvote the bot message to indicate you want to keep the issue open.

The standalone reproduction for the MCP_TIMEOUT environment setting, is present for me since 1.0.113 #7575.
You could try to perform the reproduction steps described in this issue, with the latest 2.1.7 release, as 2.0.32 is old.

[Peter4daggai]

@marcindulak I wont. And thanks for telling me that. I read it as "or comment" so i commented on my issue immediately.

I know 2.0.32 is old I was happily running my mcp tools on 2.1.4 (or 5 not sure) when last weekend it stopped working. I then reverted as far back as 2.1.1. Still did not work so I and Anthropic's support deemed it an API server issue and not Claude Code. The issue was deliberate the AI said because of some "incidents" so they took it down from 5 minutes to 1 minute. But then my colleague said he did not have the issue. I was amazed at the fact he ran it all successfully on his machine where he had 2.0.32. I reverted to that version and it also worked for me. Very strange indeed.

I also notice this issue is about the startup time of the server my issue is about MCP_TOOL_TIMEOUT i.e. the tool take about 2 minutes to return a result (transport=http)

[unbalanced]

Long starting mcps and long running mcps should be a user option
Please bring back MCP_TIMEOUT and MCP_TOOL_TIMEOUT

Also if there's a way to contribute to solving this please refer us to which codebase this belongs because i could not seem to find those implementations

[marcindulak]

People suggested in #424 (comment) that the 60 seconds limit is due to Claude Code (and Gemini CLI) somehow using the default value from https://github.com/modelcontextprotocol/typescript-sdk/blob/b0ef89ffaf6db8b3c52cd8919e8949b0f1da9ca4/packages/core/src/shared/protocol.ts#L110