What this error means
HTTP 403 / Server Turned Down — GitHub MCP OAuth flow lands on api.anthropic.com/mcp/gdrive/google/install instead of GitHub consent screen is a Claude Code failure pattern reported for developers trying to fix github mcp oauth authentication failure in claude code web sessions (claude.ai/code) where the authorization url routes to the deprecated google drive mcp install page. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
GitHub Issue #60807 (anthropics/claude-code): mcp__github__authenticate generates an authorization URL that redirects to the retired gdrive MCP endpoint, completely blocking GitHub API access in hosted web sessions. Regression — worked in previous version. Affects ALL claude.ai/code users. High commercial value: blocks paid-tier workflow.
Common causes
- GitHub Issue #60807 (anthropics/claude-code): mcp__github__authenticate generates an authorization URL that redirects to the retired gdrive MCP endpoint, completely blocking GitHub API access in hosted web sessions. Regression — worked in previous version. Affects ALL claude.ai/code users. High commercial value: blocks paid-tier workflow.
Quick fixes
- Confirm the exact error signature matches
HTTP 403 / Server Turned Down — GitHub MCP OAuth flow lands on api.anthropic.com/mcp/gdrive/google/install instead of GitHub consent screen. - 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.