What this error means
Virtual key MCP access ignores team access groups — discovery and enforcement failure is a LiteLLM failure pattern reported for developers trying to fix litellm virtual key mcp endpoints ignoring team access group restrictions. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
GitHub issue 27657 (2026-05-11) reports that virtual key MCP access completely ignores team access groups. Both discovery and enforcement are broken. Severity: High. Confirmed on v1.83.14-stable.patch.3. Affects GET /v1/mcp/server, GET /v1/mcp/toolset, POST /mcp-rest/tools/call endpoints. Not fixed in latest stable.
Common causes
- Enterprise teams using LiteLLM proxy rely on team access groups to control which tools/API keys each team can access. Virtual keys are completely bypassing these controls on MCP endpoints (GET /v1/mcp/server, GET /v1/mcp/toolset, POST /mcp-rest/tools/call). This is a security access control failure that undermines LiteLLM's enterprise team management features.
- GitHub issue 27657 (2026-05-11) reports that virtual key MCP access completely ignores team access groups. Both discovery and enforcement are broken. Severity: High. Confirmed on v1.83.14-stable.patch.3. Affects GET /v1/mcp/server, GET /v1/mcp/toolset, POST /mcp-rest/tools/call endpoints. Not fixed in latest stable.
Quick fixes
- Confirm the exact error signature matches
Virtual key MCP access ignores team access groups — discovery and enforcement failure. - Check the LiteLLM 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.