fix(ci): disable project MCP auto-load for the Claude Code Action

[BigSimmo]

Summary

• The Claude Code Action (.github/workflows/claude.yml) defaults to enableAllProjectMcpServers: true, which auto-loads this repo's .mcp.json — currently just the railway server, launched via npx @railway/cli mcp.
• In a fresh GitHub Actions runner there's no Railway session/auth, so every real @claude mention has been failing fast (~2s, is_error: true, zero turns, $0 cost) before Claude could do any actual work or post a real reply — confirmed by a live throwaway-PR test.
• Adds claude_args: --strict-mcp-config to the action step so it skips project/user MCP config entirely and runs with only its own built-in tools.

Verification

• npm run check:github-actions — pin/policy check passes on the edited workflow.
• Verification not run: npm run verify:pr-local / unit suite — this change only touches workflow YAML, no application code.
• Live verification not run in this PR: GitHub loads workflow definitions for issue_comment/pull_request_review* triggers from the default branch, not the PR head, so this fix can't be exercised by an @claude mention on its own PR before merge. I ran a live throwaway-PR test against the current (unfixed) workflow on main to diagnose the failure (Claude Code initialized → OAuth token valid, then immediate is_error crash matching the MCP-load failure mode). I'd like to re-run that same live test once this merges to main, to confirm the fix actually resolves it.

Risk and rollout

• Risk: low — additive CLI flag on an already-scoped, least-privilege workflow; no change to permissions, triggers, or the pinned action SHA.
• Rollback: revert this commit.
• Provider or production effects: None beyond the @claude Actions workflow itself.

Notes

• Once merged, I'll post a throwaway @claude test comment on a disposable PR to confirm the run now completes successfully, then report back and clean up the test PR/branch.

---

Generated by Claude Code

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 17 minutes

Your organization has reached its usage spending cap. Adjust your spending cap in the billing tab.

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 845a0b5e-0e86-4ab4-9bc8-bdca4f31e9c2

📥 Commits

Reviewing files that changed from the base of the PR and between 4bcfeb9 and 572877f.

📒 Files selected for processing (1)

• .github/workflows/claude.yml

---

_{Comment @coderabbitai help to get the list of available commands.}

[supabase]

This pull request has been ignored for the connected project sjrfecxgysukkwxsowpy because there are no changes detected in supabase directory. You can change this behaviour in Project Integrations Settings ↗︎.

---

Preview Branches by Supabase.
Learn more about Supabase Branching ↗︎.