# io.github.grahamnotgrant/blacksmith (npm · blacksmith-mcp)

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

- Trust score: 70/100 (medium)
- Change this week: +24
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `blacksmith-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/grahamnotgrant-blacksmith/blacksmith-mcp.md), [page](https://verifymcp.io/servers/grahamnotgrant-blacksmith/blacksmith-mcp)

## Channel facts

- Registry: `npm`
- Package: `blacksmith-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (130 of 134), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (130 of 134), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 194 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1727 tokens (~82/item across 21 items; 21 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add grahamnotgrant-blacksmith -- npx -y blacksmith-mcp
```

### Codex

```bash
codex mcp add grahamnotgrant-blacksmith -- npx -y blacksmith-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "grahamnotgrant-blacksmith": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "blacksmith-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add grahamnotgrant-blacksmith --command npx --arg -y --arg blacksmith-mcp
```

### Hermes

```yaml
mcp_servers:
  grahamnotgrant-blacksmith:
    command: "npx"
    args: ["-y", "blacksmith-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "grahamnotgrant-blacksmith": {
      "command": "npx",
      "args": [
        "-y",
        "blacksmith-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 70, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 66, +45)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 21, −3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 24, −22)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (21)

### `list_orgs` (~28 tokens)

List all Blacksmith organizations accessible to your account. Use this first to see available orgs.

### `get_org_status` (~25 tokens)

Get the status of the current organization (personal org, onboarding, runner region).

### `list_runs` (~171 tokens)

List workflow runs with filtering. Filter by status (success/failure/cancelled/skipped/in_progress), branch, workflow name, actor, or PR number. Example: list_runs(status="failure") to find failed runs.

Input parameters:

- `actor` (string): Filter by actor (GitHub username who triggered the run)
- `branch` (string): Filter by branch name
- `end_date` (string): End date (YYYY-MM-DD)
- `limit` (number): Maximum number of runs to return
- `pr_number` (number): Filter by pull request number
- `start_date` (string): Start date (YYYY-MM-DD)
- `status` (string): Filter by run status: success, failure, cancelled, skipped, or in_progress
- `workflow_name` (string): Filter by workflow name

### `get_run` (~37 tokens)

Get details of a specific workflow run by ID. Includes list of jobs.

Input parameters:

- `run_id` (string, required): GitHub Actions workflow run ID

### `list_jobs` (~50 tokens)

List all jobs for a specific workflow run. Use this to get job IDs for get_job, get_job_logs, and get_job_tests.

Input parameters:

- `run_id` (string, required): GitHub Actions workflow run ID

### `get_job` (~50 tokens)

Get details of a specific job including steps, runner info, and timing.

Input parameters:

- `job_id` (string, required): GitHub Actions job ID
- `run_id` (string, required): GitHub Actions workflow run ID

### `get_job_logs` (~68 tokens)

Get the logs for a specific job. Returns raw log output.

Input parameters:

- `job_id` (string, required): GitHub Actions job ID
- `limit` (number): Maximum number of log lines (default: 1000)
- `vm_id` (string): VM ID for the job (optional)

### `get_job_tests` (~109 tokens)

Get test results for a job. Optionally filter by status (pass/fail/skip).

Input parameters:

- `include_tests` (boolean): Include individual test details (default: false, returns summary only)
- `job_id` (string, required): GitHub Actions job ID
- `limit` (number): Maximum number of tests to return when include_tests is true (default: 50)
- `run_id` (string, required): GitHub Actions workflow run ID
- `status` (string): Filter by test status

### `get_failed_tests` (~130 tokens)

Get failed tests for a job with full error details. Use error_lines param to control stack trace length. Returns all failures by default (no limit).

Input parameters:

- `error_lines` (number): Number of error lines to include per test (default: 5, max: 50)
- `job_id` (string, required): GitHub Actions job ID
- `limit` (number): Maximum number of failed tests to return (default: all)
- `run_id` (string, required): GitHub Actions workflow run ID
- `suite` (string): Filter by test suite name (e.g., "FeatureFlags Middleware")

### `get_failures_by_pattern` (~100 tokens)

Group failed tests by error pattern (e.g., "is not a function", "Cannot read properties"). Shows count, affected suites/files, and sample error for each pattern. Best for quickly identifying root causes.

Input parameters:

- `job_id` (string, required): GitHub Actions job ID
- `run_id` (string, required): GitHub Actions workflow run ID
- `top_n` (number): Number of top error patterns to return (default: 10)

### `compare_test_runs` (~111 tokens)

Compare test failures between two runs to identify regressions. Shows new failures, fixed tests, and persistent failures. If base_run_id not provided, compares against most recent prior run.

Input parameters:

- `base_run_id` (string): Base run ID to compare against. If not provided, compares against most recent prior run.
- `job_name` (string, required): Job name to compare (e.g., "Test (Blacksmith/Self-Hosted)")
- `run_id` (string, required): Current GitHub Actions workflow run ID

### `get_flaky_tests` (~154 tokens)

Detect flaky tests by analyzing pass/fail patterns across recent runs. Returns tests that fail intermittently (e.g., "failed 3 of 10 runs"). Killer feature for CI stability.

Input parameters:

- `days` (number): Number of days to analyze (default: 7)
- `job_name` (string, required): Job name to analyze (e.g., "Test (Blacksmith/Self-Hosted)")
- `min_runs` (number): Minimum number of runs a test must appear in to be considered (default: 3)
- `threshold` (number): Flakiness threshold 0-1, e.g., 0.2 means test failed 20%+ of runs (default: 0.1)

### `get_slow_tests` (~103 tokens)

Find tests exceeding a duration threshold. Shows slowest tests, their percentage of total test time, and average duration stats.

Input parameters:

- `job_id` (string, required): GitHub Actions job ID
- `limit` (number): Maximum number of slow tests to return (default: 20)
- `run_id` (string, required): GitHub Actions workflow run ID
- `threshold_ms` (number): Duration threshold in milliseconds (default: 5000ms = 5s)

### `get_test_history` (~118 tokens)

Get the failure history for a specific test across recent runs. Shows when it passed/failed, on which branches, and error messages for failures.

Input parameters:

- `job_name` (string, required): Job name to search in (e.g., "Test (Blacksmith/Self-Hosted)")
- `limit` (number): Number of historical results to return (default: 10)
- `suite` (string): Test suite name (helps disambiguate if multiple tests have same name)
- `test_name` (string, required): Name of the test to look up

### `get_trends` (~133 tokens)

Track metrics over time: duration (are tests getting slower?), failure_rate (are tests getting flakier?), test_count (are we adding tests?). Returns trend analysis with data points.

Input parameters:

- `days` (number): Number of days to analyze (default: 14)
- `granularity` (string): Group data by day or week (default: day)
- `job_name` (string, required): Job name to analyze (e.g., "Test (Blacksmith/Self-Hosted)")
- `metric` (string, required): Metric to track: duration (job runtime), failure_rate (% tests failing), test_count (total tests)

### `get_current_usage` (~21 tokens)

Get current core usage snapshot (active cores vs max cores).

### `get_invoice_amount` (~17 tokens)

Get the current billing period invoice amount.

### `get_usage_summary` (~29 tokens)

Get usage summary showing billable minutes vs free tier allowance. Shows remaining free minutes and overage.

### `get_cache_stats` (~49 tokens)

Get Blacksmith cache statistics: total size, hit rate, entries by repository. Shows how effectively caching is being used.

Input parameters:

- `include_history` (boolean): Include historical cache data (default: false)

### `get_cache_entries` (~95 tokens)

Get detailed cache entries for a repository. Shows cache keys, sizes, scopes (branches), and last hit times. Useful for debugging cache issues.

Input parameters:

- `limit` (number): Maximum number of entries to return (default: 20)
- `repository` (string, required): Repository name - try short name first (e.g., "votion"), or full name (e.g., "Votion-Platform/votion") if needed

### `search_logs` (~129 tokens)

Search logs across all jobs. Filter by query (e.g., "error", "timeout"), log level (INFO/WARN/ERROR/DEBUG), and time range. Great for finding issues across runs.

Input parameters:

- `hours` (number): Number of hours to search back (default: 1, max: 24)
- `level` (string): Filter by log level
- `limit` (number): Maximum number of logs to return (default: 100)
- `query` (string): Search query (e.g., "error", "timeout", "failed"). Leave empty to get all logs.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/grahamnotgrant-blacksmith/blacksmith-mcp#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 66
- 2026-08-01: 21
- 2026-07-31: 21
- 2026-07-30: 24
- 2026-07-28: 24
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/blacksmith-mcp
- Socket report: https://socket.dev/npm/package/blacksmith-mcp
- Repository: https://github.com/grahamnotgrant/blacksmith-mcp
- Changelog RSS feed: https://verifymcp.io/servers/grahamnotgrant-blacksmith/blacksmith-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/grahamnotgrant-blacksmith/blacksmith-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/grahamnotgrant-blacksmith/blacksmith-mcp