Skip to main content
Glama

ci-triage-mcp

MCP server for GitHub Actions CI failure triage. Wraps the gh CLI to fetch PR checks, failed jobs, and tail/grep failed job logs — with ANSI/timestamp stripping and root-cause extraction. Zero runtime dependencies; stdio JSON-RPC.

Built to turn a 5–10 minute "open the run, find the failed job, scroll the raw log" ritual into a single tool call.

Tools

Tool

Input

Returns

get_pr_checks

repo, prNumber

Aggregated check rollup: failed / pending / success + merge state

get_failed_jobs

repo, runId

Jobs with conclusion=failure: name, databaseId, url, timestamps

get_job_logs_tail

repo, jobId, lines?

Last N log lines, ANSI + timestamp prefixes stripped

grep_job_logs

repo, jobId, pattern, maxMatches?

Matching lines + 2 lines context. Use when failure is mid-log (E2E, build errors)

summarize_pr_failure

repo, prNumber

End-to-end: failed checks → failed jobs → log tail → extracted error lines + file:line

All repo inputs validated as owner/repo (alphanumerics, ., -, _). lines capped at 500, maxMatches at 200.

Related MCP server: tai-mcp-github

Install

One-click install

Click a badge → opens the install page → click the button → your IDE prompts to install.

Add to Cursor Add to VS Code

GitHub strips custom protocol schemes (cursor://, vscode://) from markdown links for security, so the badges route through a hosted install page on GitHub Pages with real <a href> buttons. The page also covers Claude Code, Claude Desktop, Cline, Windsurf, Zed, and LM Studio.

The install page registers the server under the name ci-triage via npx -y github:aamar-shahzad/ci-triage-mcp (works now, no npm registry publish needed). After install, restart your IDE if the tools don't appear immediately.

Manual install — per client

The server config is the same everywhere; only the file location differs.

Cursor — ~/.cursor/mcp.json:

{
  "mcpServers": {
    "ci-triage": {
      "command": "npx",
      "args": ["-y", "github:aamar-shahzad/ci-triage-mcp"],
      "env": {}
    }
  }
}

VS Code / GitHub Copilot — ~/.vscode/mcp.json (or workspace .vscode/mcp.json):

{
  "mcpServers": {
    "ci-triage": {
      "command": "npx",
      "args": ["-y", "github:aamar-shahzad/ci-triage-mcp"],
      "env": {}
    }
  }
}

Claude Desktop — claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ci-triage": {
      "command": "npx",
      "args": ["-y", "github:aamar-shahzad/ci-triage-mcp"],
      "env": {}
    }
  }
}

Claude Code (CLI):

claude mcp add ci-triage npx -- -y github:aamar-shahzad/ci-triage-mcp

Cline / Roo Code / Continue / Windsurf — same mcpServers shape as Cursor, in their respective MCP config files:

  • Cline: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json (macOS)

  • Windsurf: ~/.codeium/windsurf/mcp_config.json

  • Continue: ~/.continue/config.json under experimental.mcpServers

Zed — ~/.config/zed/settings.json:

{
  "context_servers": {
    "ci-triage": {
      "command": "npx",
      "args": ["-y", "github:aamar-shahzad/ci-triage-mcp"],
      "env": {}
    }
  }
}

LM Studio — deep link:

lmstudio://add_mcp?name=ci-triage&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImdpdGh1YjphYW1hci1zaGFoemFkL2NpLXRyaWFnZS1tY3AiXSwiZW52Ijp7fX0=

Option C — clone + run directly

For local development or to avoid npx cold-install delay:

git clone https://github.com/aamar-shahzad/ci-triage-mcp.git ~/src/ci-triage-mcp

Then in your MCP config:

{
  "mcpServers": {
    "ci-triage": {
      "command": "node",
      "args": ["/Users/you/src/ci-triage-mcp/src/index.mjs"]
    }
  }
}
node scripts/gen-install-links.mjs          # prints markdown
node scripts/gen-install-links.mjs --json   # prints raw links as JSON

Authentication

No token stored in MCP config. Uses your existing gh CLI authentication (keyring / config file from gh auth login). The server shells out to gh; nothing else.

Requirements:

  • gh CLI on PATH — install from https://cli.github.com

  • Authenticated: gh auth login (scopes: repo, workflow for CI logs)

  • Node ≥ 20

On initialize, the server probes gh --version and emits a _warning in serverInfo if gh is missing.

Why

Generic GitHub MCPs return raw JSON and stop at the check rollup. This server is opinionated about the triage workflow:

  1. Failed-check discovery — get_pr_checks filters to conclusion=FAILURE only.

  2. Job drilldown — get_failed_jobs maps a run to its failed job IDs (the part you usually copy by hand).

  3. Clean logs — get_job_logs_tail strips ANSI escapes and the 2026-07-09T20:34:56.5281699Z timestamp prefix that buries the actual line.

  4. Mid-log grep — grep_job_logs finds errors anywhere in the log with context. E2E / build failures live mid-log, not at the tail. Tail-only tools miss them.

  5. Root-cause extraction — summarize_pr_failure chains all of the above and extracts error lines + file:line in one call.

Example: a 725-line Cypress job log → grep_job_logs with pattern AssertionError|Timed out returns 1 match with 2 lines context, surfacing Expected to find element: [data-testid="inviteUserButton"], but never found it in one call.

Smoke test

node scripts/smoke.mjs

Runs tools/list + a grep_job_logs call against a known public failed job. Requires gh auth.

Development

git clone https://github.com/aamar-shahzad/ci-triage-mcp.git
cd ci-triage-mcp
node src/index.mjs   # starts stdio JSON-RPC server

No build step. Pure ESM .mjs, no dependencies.

License

MIT

Available Tools

5 tools
get_failed_jobsA

List only failed jobs for a workflow run. Input: {repo: "owner/repo", runId: number}. Returns jobs with conclusion=failure: name, databaseId, url.

Inputs: repo (required), runId (required).

get_job_logs_tailA

Fetch tail of a failed job log. Input: {repo: "owner/repo", jobId: number, lines?: number=80}. Returns last N lines of the job log (cleaned of ANSI + timestamp prefixes).

Inputs: repo (required), jobId (required), lines.

get_pr_checksA

List all CI checks for a GitHub PR with conclusion + URL. Input: {repo: "owner/repo", prNumber: number}. Returns aggregated check rollup.

Inputs: repo (required), prNumber (required).

grep_job_logsA

Grep a job log for lines matching a regex (case-insensitive). Returns matching lines with 2 lines context before/after. Use when failure is mid-log (E2E tests, build errors) rather than at the tail. Input: {repo, jobId, pattern: string, maxMatches?: number=50}.

Inputs: repo (required), jobId (required), pattern (required), maxMatches.

summarize_pr_failureA

End-to-end triage: find failed checks on a PR, tail each failed job log, extract error/fail/first-failing-test lines. Input: {repo, prNumber}. Returns per-failed-job summary with likely root cause.

Inputs: repo (required), prNumber (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a distinct purpose: listing failed jobs, fetching log tails, listing all checks, searching logs, and summarizing failures. No overlap or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (e.g., get_failed_jobs, grep_job_logs), making it predictable.

    Tool Count5/5

    Five tools is appropriate for CI triage—covers listing, log access, searching, and summarization without being excessive or insufficient.

    Completeness5/5

    The tool set covers the full triage workflow: identify failures, retrieve logs, search logs, and generate summaries. No obvious gaps for the stated purpose.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers