Blacksmith

io.github.grahamnotgrantPublished by GitHub account grahamnotgrantv0.1.1Updated Oct 24, 2026

MCP server for Blacksmith CI - query runs, analyze test failures, detect flaky tests.

Overview

AI-generated overview

Lets an assistant query Blacksmith CI workflow runs, analyze test failures, detect flaky tests, and check usage and billing.

What you can do
Connects an assistant to Blacksmith CI data through tools for listing and inspecting workflow runs, jobs, and job logs. Test analytics tools return failed tests, failures grouped by error pattern, comparisons between two runs, flaky and slow tests, per-test history, and trends. Further tools report core usage, invoice amount, usage summary, cache statistics and entries, plus organization listing, org status, and cross-job log search.
When to use it
Useful when a team runs CI on Blacksmith and wants to debug failed runs, find flaky or slow tests, compare failures between a pull request and its base branch, or check usage and cache consumption conversationally instead of clicking through dashboards.
Requirements
Runs locally over stdio, typically via npx blacksmith-mcp, so Node.js is needed. Requires the BLACKSMITH_ORG environment variable. Authentication is either automatic extraction of the session cookie from Chrome on macOS or the BLACKSMITH_SESSION_COOKIE environment variable set manually. Network access to Blacksmith's API is required.
Before you install
The server reads a logged-in Blacksmith session: by default it extracts the session cookie from Chrome, and the BLACKSMITH_SESSION_COOKIE variable holds a credential that grants account access. It relies on Blacksmith's undocumented internal web API, which was reverse-engineered and may change without notice. Tools are read-oriented, but usage and billing figures are exposed.

Installation

In SourceWeft

  1. Open Blacksmith in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Blacksmith MCP

[npm version] [License: MIT] [MCP]

An MCP server that connects Claude to your Blacksmith CI data. Query workflow runs, analyze test failures, detect flaky tests, and monitor usage—all through natural conversation.

Why?

Debugging CI failures usually means clicking through dashboards, copying run IDs, and piecing together information across multiple pages. With this MCP, you can just ask:

  • "Why did the last CI run fail?"
  • "Which tests are flaky this week?"
  • "Compare test failures between main and my PR"
  • "What's using the most cache storage?"

Claude handles the API calls and gives you actionable insights.

Quick Start

Zero-config if you're logged into Blacksmith in Chrome:

bash
# Add to Claude Codeclaude mcp add blacksmith -- npx blacksmith-mcp
# Set your org (run once)export BLACKSMITH_ORG="your-org-name"

The MCP automatically extracts your session from Chrome cookies. No manual token copying needed.

Installation

Option 1: Claude Code CLI

bash
claude mcp add blacksmith -- npx blacksmith-mcp

Option 2: Project Configuration

Add to your .mcp.json:

json
{  "mcpServers": {    "blacksmith": {      "type": "stdio",      "command": "npx",      "args": ["blacksmith-mcp"],      "env": {        "BLACKSMITH_ORG": "your-org-name"      }    }  }}

Option 3: Global Install

bash
npm install -g blacksmith-mcp

Configuration

Authentication

Automatic (recommended): Log into app.blacksmith.sh in Chrome. The MCP extracts your session cookie automatically.

Manual: Set BLACKSMITH_SESSION_COOKIE environment variable with your session cookie value.

Environment Variables

VariableRequiredDescription
BLACKSMITH_ORGYesYour Blacksmith organization name
BLACKSMITH_SESSION_COOKIENoSession cookie (auto-extracted from Chrome if not set)

Available Tools

Workflow Runs

ToolDescription
list_runsList workflow runs with filters (status, branch, workflow, actor, PR)
get_runGet run details including all jobs
list_jobsList jobs for a workflow run
get_jobGet job details (steps, timing, runner info)
get_job_logsGet raw log output for a job

Test Analytics

ToolDescription
get_job_testsGet all test results for a job
get_failed_testsGet failed tests with full error messages
get_failures_by_patternGroup failures by error pattern (e.g., "Cannot read properties")
compare_test_runsCompare failures between two runs (find regressions)
get_flaky_testsDetect tests that fail intermittently
get_slow_testsFind tests exceeding duration threshold
get_test_historyTrack a specific test's pass/fail history
get_trendsAnalyze trends: duration, failure rate, test count

Usage & Billing

ToolDescription
get_current_usageCurrent core usage (active vs max)
get_invoice_amountCurrent billing period amount
get_usage_summaryBillable minutes vs free tier
get_cache_statsCache size, entries by repository
get_cache_entriesDetailed cache entries for a repo

Organization

ToolDescription
list_orgsList accessible organizations
get_org_statusOrg status (personal, onboarded, region)
search_logsSearch logs across all jobs

Example Conversations

Debug a Failed Run

You: Why did the last CI run fail?

Claude: Uses list_runs(status="failure", limit=1) then get_failed_tests

The last run failed with 34 test failures. The main issues are:

  • Connection timeout (12 tests) - Tests in api/ are timing out connecting to the test database
  • Undefined property (8 tests) - user.settings.theme is undefined in the new dark mode code
  • Assertion failures (14 tests) - Snapshot mismatches in UI components

Find Flaky Tests

You: Which tests are flaky?

Claude: Uses get_flaky_tests(days=7, min_runs=5)

Found 3 flaky tests:

TestFlake RatePattern
should handle concurrent requests40% (4/10 runs)Fails on CI, passes locally
renders loading state20% (2/10 runs)Race condition with setTimeout
validates auth token30% (3/10 runs)Intermittent network timeout

Compare Branches

You: Did my PR introduce new test failures?

Claude: Uses compare_test_runs with PR run vs base branch

Your PR introduced 2 new failures:

  • UserProfile.test.tsx: "Cannot read property 'avatar' of undefined"
  • api/users.test.ts: Expected 200, got 404

5 previously failing tests now pass (nice!).

Development

bash
# Install dependenciespnpm install
# Buildpnpm build
# Development mode (watch)pnpm dev
# Test with MCP Inspectornpx @modelcontextprotocol/inspector node dist/index.js

Troubleshooting

Session Expired

If you see SESSION_EXPIRED, your Blacksmith session has expired. Simply log back into app.blacksmith.sh in Chrome and retry.

Cookie Extraction Failed

The automatic cookie extraction requires:

  • macOS with Chrome installed
  • Being logged into Blacksmith in Chrome
  • Chrome not running with a locked profile

If it fails, set BLACKSMITH_SESSION_COOKIE manually.

No Organization Set

Run list_orgs to see available organizations, then set BLACKSMITH_ORG to your org name.

API Notes

This MCP uses Blacksmith's internal web API, which is undocumented. The API was reverse-engineered from the Blacksmith web app and may change without notice.

License

MIT

Contributing

Contributions welcome! Please open an issue first to discuss proposed changes.

Source: README.md at commit f9ea93d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts