Claude Code --strict-mcp-config still fetches MCP registry despite empty config

What this error means

--strict-mcp-config with empty --mcp-config still fetches MCP registry from api.anthropic.com and attempts user-configured servers is a Claude Code failure pattern reported for developers trying to fix mcp server configuration being ignored when using strict mode; prevent unwanted network calls to mcp registry. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue #60252 on anthropics/claude-code repo: —strict-mcp-config flag claims to only use MCP servers from —mcp-config but still reaches out to api.anthropic.com registry. Created 2026-05-18. Category mapping: Claude Code → AI Coding Tools per approved category rules.

Common causes

• GitHub issue #60252 on anthropics/claude-code repo: —strict-mcp-config flag claims to only use MCP servers from —mcp-config but still reaches out to api.anthropic.com registry. Created 2026-05-18. Category mapping: Claude Code → AI Coding Tools per approved category rules.

Quick fixes

1. Confirm the exact error signature matches --strict-mcp-config with empty --mcp-config still fetches MCP registry from api.anthropic.com and attempts user-configured servers.
2. Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
3. 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

1. Capture the exact error message and the command, editor action, or request that triggered it.
2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
3. Review the source evidence below and compare it with your environment.
4. Apply one change at a time and rerun the smallest failing action.
5. 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.

Sources checked

• https://github.com/anthropics/claude-code/issues/60252

Evidence note: GitHub issue #60252 on anthropics/claude-code repo: —strict-mcp-config flag claims to only use MCP servers from —mcp-config but still reaches out to api.anthropic.com registry. Created 2026-05-18. Category mapping: Claude Code → AI Coding Tools per approved category rules.

Related errors

• AI Coding Tools

FAQ

What should I check first?

Start with the exact --strict-mcp-config with empty --mcp-config still fetches MCP registry from api.anthropic.com and attempts user-configured servers text and the smallest action that reproduces it.

Can I ignore this error?

No. Treat it as a failed Claude Code workflow until the root cause is understood.

Is this guaranteed to have one fix?

No. The imported evidence supports the troubleshooting path above, but tool behavior can vary by account, plan, version, provider, and local configuration.

How do I know the fix worked?

Rerun the same command, editor action, or request. The fix is working when that action completes without --strict-mcp-config with empty --mcp-config still fetches MCP registry from api.anthropic.com and attempts user-configured servers.