What this error means

mcp auth not automatically launching browser on Windows — no errors, just no activity after clicking Authenticate is a Claude Code failure pattern reported for developers trying to fix mcp oauth authentication flow where claude code fails to launch browser for atlassian, datadog, slack, sourcegraph integrations on windows with git bash + ssh. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub Issue #59194 on anthropics/claude-code (open, bug + regression label, platform:windows). Regression introduced in v2.1.141 — auto-updated on 2026-05-14. Browser-open logic no longer falls back to cmd.exe /c start when BROWSER is unset and DISPLAY empty in Git Bash/MSYS2 under SSH/PLink context. Clear work-around available but affects paying pro/teams users doing daily MCP auth.

Common causes

  • GitHub Issue #59194 on anthropics/claude-code (open, bug + regression label, platform:windows). Regression introduced in v2.1.141 — auto-updated on 2026-05-14. Browser-open logic no longer falls back to cmd.exe /c start when BROWSER is unset and DISPLAY empty in Git Bash/MSYS2 under SSH/PLink context. Clear work-around available but affects paying pro/teams users doing daily MCP auth.

Quick fixes

  1. Confirm the exact error signature matches mcp auth not automatically launching browser on Windows — no errors, just no activity after clicking Authenticate.
  2. Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
  3. 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

  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.