What this error means
Disabled MCP servers still trigger OAuth authentication popups in Claude Code — interrupts automated headless workflows is a Claude Code failure pattern reported for developers trying to user disables certain mcp servers in claude code settings but disabled servers keep triggering oauth popup prompts, breaking ci/cd automation and headless usage patterns. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
Found on GitHub: anthropics/claude-code#31648 (Mar 2026). Title: 'Disabled MCP servers still trigger OAuth authentication ...'. Describes: go to /mcp, disable several servers, confirm — but they still prompt for OAuth. Affects automation users and enterprise setups heavily.
Common causes
- Found on GitHub: anthropics/claude-code#31648 (Mar 2026). Title: 'Disabled MCP servers still trigger OAuth authentication ...'. Describes: go to /mcp, disable several servers, confirm — but they still prompt for OAuth. Affects automation users and enterprise setups heavily.
Quick fixes
- Confirm the exact error signature matches
Disabled MCP servers still trigger OAuth authentication popups in Claude Code — interrupts automated headless workflows. - Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
- Verify the account session, API key, provider settings, and environment where the failing tool is running.
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.