Blacksmith
Connects Claude to Blacksmith CI's internal web API for debugging test failures and monitoring builds. Query workflow runs with filters for status, branch, or PR. Analyze test results with tools like get_failed_tests, get_flaky_tests, and compare_test_runs to spot regressions between branches. Search logs, track test history, and check cache usage across repositories. Authentication works through Chrome cookie extraction if you're logged into app.blacksmith.sh, otherwise pass a session token manually. Useful when you're triaging CI failures and want to ask "why did this run fail" or "which tests are flaky this week" instead of clicking through dashboards.
- GitHub stars
- 2
- tools
- 21
- auth
- Secret needed
- transport
- STDIO
- env vars
- 2
- last updated
- Jan 20, 2026
Tools
21 toolsPublic tool metadata for what this MCP can expose to an agent.
list_runsList workflow runs with filters (status, branch, workflow, actor, PR)
List workflow runs with filters (status, branch, workflow, actor, PR)
No parameter schema in public metadata yet.
get_runGet run details including all jobs
Get run details including all jobs
No parameter schema in public metadata yet.
list_jobsList jobs for a workflow run
List jobs for a workflow run
No parameter schema in public metadata yet.
get_jobGet job details (steps, timing, runner info)
Get job details (steps, timing, runner info)
No parameter schema in public metadata yet.
get_job_logsGet raw log output for a job
Get raw log output for a job
No parameter schema in public metadata yet.
get_job_testsGet all test results for a job
Get all test results for a job
No parameter schema in public metadata yet.
get_failed_testsGet failed tests with full error messages
Get failed tests with full error messages
No parameter schema in public metadata yet.
get_failures_by_patternGroup failures by error pattern (e.g., "Cannot read properties")
Group failures by error pattern (e.g., "Cannot read properties")
No parameter schema in public metadata yet.
compare_test_runsCompare failures between two runs (find regressions)
Compare failures between two runs (find regressions)
No parameter schema in public metadata yet.
get_flaky_testsDetect tests that fail intermittently
Detect tests that fail intermittently
No parameter schema in public metadata yet.
get_slow_testsFind tests exceeding duration threshold
Find tests exceeding duration threshold
No parameter schema in public metadata yet.
get_test_historyTrack a specific test's pass/fail history
Track a specific test's pass/fail history
No parameter schema in public metadata yet.
get_trendsAnalyze trends: duration, failure rate, test count
Analyze trends: duration, failure rate, test count
No parameter schema in public metadata yet.
get_current_usageCurrent core usage (active vs max)
Current core usage (active vs max)
No parameter schema in public metadata yet.
get_invoice_amountCurrent billing period amount
Current billing period amount
No parameter schema in public metadata yet.
get_usage_summaryBillable minutes vs free tier
Billable minutes vs free tier
No parameter schema in public metadata yet.
get_cache_statsCache size, entries by repository
Cache size, entries by repository
No parameter schema in public metadata yet.
get_cache_entriesDetailed cache entries for a repo
Detailed cache entries for a repo
No parameter schema in public metadata yet.
list_orgsList accessible organizations
List accessible organizations
No parameter schema in public metadata yet.
get_org_statusOrg status (personal, onboarded, region)
Org status (personal, onboarded, region)
No parameter schema in public metadata yet.
search_logsSearch logs across all jobs
Search logs across all jobs
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
BLACKSMITH_ORG*Your Blacksmith organization name
BLACKSMITH_SESSION_COOKIEsecretSession cookie (auto-extracted from Chrome if not set)
Readme
Blacksmith 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:
# Add to Claude Code
claude mcp add blacksmith -- npx blacksmith-mcp
# Set your org (run once)
export BLACKSMITH_ORG="your-org-name"
Details
- Repository
- github.com/grahamnotgrant/blacksmith-mcp
- Package
blacksmith-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active