MCP Inspector - Still failing after TAVILY_API_KEY fix (0% success rate, 20 days offline)

[github-actions]

Problem

MCP Inspector workflow remains non-operational with 0% success rate despite TAVILY_API_KEY secret being added. The workflow has been offline for 20 days.

Current Status (2026-01-25)

• Success rate: 0/5 recent runs (0%)
• Latest failure: §21304877267 (2026-01-23)
• Days offline: 20 days (since 2026-01-05)
• Failed step: "Start MCP gateway" (step 24)
• Previous issue: Fix MCP Inspector workflow - "Start MCP gateway" failure (80% failure rate) #11433 (auto-closed 2026-01-24)

Root Cause Analysis

Key insight: Daily News workflow recovered immediately after TAVILY_API_KEY was added (2026-01-22), but MCP Inspector did NOT recover. This suggests:

1. Hypothesis 1: Workflow needs recompilation

   • Secret was added AFTER last compilation
   • Lock file may not reference the new secret
   • Solution: make recompile

2. Hypothesis 2: Different MCP Gateway configuration

   • MCP Inspector may use different MCP server setup than Daily News
   • May need additional configuration beyond TAVILY_API_KEY
   • Review frontmatter differences

3. Hypothesis 3: MCP Gateway version incompatibility

   • Check Docker container versions
   • Verify MCP Gateway version matches requirements

Comparison with Daily News

Aspect	Daily News (✅ Working)	MCP Inspector (❌ Failing)
TAVILY_API_KEY	Present	Present
Recovery	Immediate (2026-01-22)	None
Success rate	40% (recovering)	0% (failing)
Last compiled	Unknown	Unknown
MCP Gateway	Working	Failing at startup

Recommended Investigation Steps

Step 1: Recompile Workflow

cd /path/to/repo
make recompile
git add .github/workflows/mcp-inspector.lock.yml
git commit -m "Recompile MCP Inspector after TAVILY_API_KEY fix"
git push

Step 2: Compare Frontmatter

Compare configurations:

• .github/workflows/daily-news.md (working)
• .github/workflows/mcp-inspector.md (failing)

Look for differences in:

• MCP server configuration
• Tool permissions
• Environment variables

Step 3: Analyze Failed Run Logs

Download artifacts from run 21304877267:

• Check /tmp/gh-aw/mcp-logs/ for MCP Gateway errors
• Review agent stdio logs
• Look for secret access issues

Step 4: Test Manually

gh workflow run mcp-inspector.lock.yml

Monitor run and check logs immediately.

Success Criteria

• MCP Inspector runs successfully
• "Start MCP gateway" step completes without errors
• Success rate returns to >80% over next 5 runs
• MCP tooling inspection capabilities restored

Priority: P1 (High)

Impact: Critical tooling for MCP debugging offline for 20 days. This blocks MCP server development and troubleshooting.

Urgency: High - affecting developer productivity and MCP ecosystem health.

Next steps:

1. Recompile workflow (5 min)
2. Test manually (10 min)
3. Analyze results and iterate (30 min)

References:

• Latest failed run §21304877267
• Workflow source
• Previous issue #11433 (auto-closed)
• Dashboard #11581

AI generated by Workflow Health Manager - Meta-Orchestrator

• expires on Jan 26, 2026, 3:08 AM UTC

[github-actions]

🍪 Issue Monster has assigned this to Copilot!

I've identified this issue as a good candidate for automated resolution and assigned it to the Copilot agent.

The Copilot agent will analyze the issue and create a pull request with the fix.

Om nom nom! 🍪

AI generated by Issue Monster

[github-actions]

This issue was automatically closed because it expired on 2026-01-26T03:08:02.793Z.