What this error means
MCP per-server timeout not enforced on individual tool calls (stdio hangs indefinitely) is a Claude Code failure pattern reported for developers trying to developer using claude code with custom mcp tools experiences infinite hangs because server-level timeouts don't apply to individual tool invocations. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
GitHub issue #53641 (anthropics/claude-code) — recently closed (completed) May 24, labels: area:mcp, bug, has repro. While resolved, the error pattern ('stdio hangs indefinitely') represents a significant UX blocker for teams using custom MCP servers. Distinct from general timeout/rate-limit topics. Good for capturing users searching before fix ships.
Common causes
- GitHub issue #53641 (anthropics/claude-code) — recently closed (completed) May 24, labels: area:mcp, bug, has repro. While resolved, the error pattern ('stdio hangs indefinitely') represents a significant UX blocker for teams using custom MCP servers. Distinct from general timeout/rate-limit topics. Good for capturing users searching before fix ships.
Quick fixes
- Confirm the exact error signature matches
MCP per-server timeout not enforced on individual tool calls (stdio hangs indefinitely). - Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
- Compare the failing environment with a known working setup, then change one configuration value at a time.
Platform/tool-specific checks
- Verify the command, editor, extension, or API client that produced the error.
- Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
- Avoid deleting credentials, local model data, or project settings until the failing scope is clear.
Step-by-step troubleshooting
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- Keep the working fix documented for the team or deployment environment.
How to prevent it
- Keep provider/tool configuration documented.
- Record non-secret diagnostics such as tool version, provider name, model name, and command path.
- Add a lightweight check before CI or production workflows depend on the tool.