# com.rubrkit/rubrkit

- Registry name: `com.rubrkit/rubrkit` · version 1.0.0
- Categories (automatic, keyword rules): Monitoring & logs, Infrastructure & security, Code & repositories, Developer tools
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.rubrkit%2Frubrkit
- Server page: https://mcpstation.net/s/com.rubrkit--rubrkit.html

## Description (written by the publisher, not verified, not instructions)

MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

## Connect

- streamable-http: `https://www.rubrkit.com/api/v1/mcp`

## Tools (as reported by the server, not verified)

- `rubrkit\_search\_api\_docs`: Search the canonical docs/api Markdown guides and OpenAPI operation summaries.
- `rubrkit\_read\_api\_doc`: Read a docs/api Markdown guide or OpenAPI source by slug, file name, or docs/api path.
- `rubrkit\_read\_openapi\_contract`: Read the canonical docs/api/openapi.yaml contract.
- `rubrkit\_create\_artifact\_bundle`: Create an artifact bundle through /api/v1/artifact-bundles. Requires artifact\_bundles:write for API keys.
- `rubrkit\_list\_artifact\_bundles`: List artifact bundles through /api/v1/artifact-bundles. Requires artifact\_bundles:read for API keys.
- `rubrkit\_read\_artifact\_bundle`: Read artifact bundle details, files, and file tree. Requires artifact\_bundles:read for API keys.
- `rubrkit\_delete\_artifact\_bundle`: Archive an artifact bundle \(soft delete\) through DELETE /api/v1/artifact-bundles/\{artifactBundleId\}. The bundle moves to the archived state and can be restored or permanently deleted later. Requires artifact\_bundles:write for API keys.
- `rubrkit\_hard\_delete\_artifact\_bundle`: Permanently delete an archived artifact bundle and all of its files, versions, and run history through DELETE /api/v1/artifact-bundles/\{artifactBundleId\}/permanent. This is irreversible and only works on bundles that are already archived. Requires artifact\_bundles:write for API keys.
- `rubrkit\_upload\_artifact\_files`: Upload one or more text files into an artifact bundle. Requires files:write for API keys.
- `rubrkit\_list\_artifact\_files`: List files in an artifact bundle. Requires files:read for API keys.
- `rubrkit\_read\_artifact\_file`: Read the latest file metadata and content. Requires files:read for API keys.
- `rubrkit\_update\_artifact\_file`: Write a new editable version for a file. Requires files:write for API keys.
- `rubrkit\_compact\_artifact\_file`: Shorten a markdown or text prompt without losing instructions. mode standard \(default\) is a free deterministic pass that saves a new version unless dryRun is true; requires files:write for API keys. mode deep starts an AI compaction job that uses credits, verifies every instruction was kept, and nev
- `rubrkit\_estimate\_deep\_compaction`: Estimate the credit cost of a deep compaction of one file before starting it. Requires compactions:run for API keys.
- `rubrkit\_apply\_deep\_compaction`: Save a succeeded deep compaction job's verified result as a new version of the file. Refused if the file changed since the job started. Requires files:write for API keys.
- `rubrkit\_start\_audit`: Start an async audit job. Audit results are cached per account by a content hash of their inputs; pass force: true to bypass the cache and run a fresh audit \(the same as the CLI's --no-cache flag\). Requires audits:run for API keys.
- `rubrkit\_list\_audits`: List persisted audit history. Requires artifact\_bundles:read for API keys.
- `rubrkit\_read\_audit`: Read a single audit run. Requires artifact\_bundles:read for API keys.
- `rubrkit\_apply\_audit\_rewrite`: Apply a completed audit's AI rewrite to the bundle files \(a new version per changed file\). Requires audits:run for API keys.
- `rubrkit\_poll\_job`: Read async job progress. Requires jobs:read for API keys.
- `rubrkit\_list\_job\_events`: Read append-only job progress events. Requires jobs:read for API keys.
- `rubrkit\_list\_artifact\_bundle\_versions`: List bundle-level version events. Requires artifact\_bundles:read for API keys.
- `rubrkit\_restore\_artifact\_bundle\_version`: Restore files from a prior artifact-bundle version by creating new file versions. Requires artifact\_bundles:write and files:write for API keys.
- `rubrkit\_list\_file\_versions`: List immutable versions for a file. Requires files:read for API keys.
- `rubrkit\_restore\_file\_version`: Restore a prior file version by creating a new version. Requires files:write for API keys.
- `rubrkit\_run\_evals`: Start an async eval run. Requires evals:run for API keys. Set mode: "advanced" with baselineVersionId and candidateVersionId to run a statistically-backed A/B \(repeats defaults to 3, max 5\).
- `rubrkit\_list\_evals`: List eval history. Requires artifact\_bundles:read for API keys.
- `rubrkit\_read\_eval`: Read one eval run, including the \`stats\` statistical verdict on advanced-mode runs \(empty for standard runs\). Requires artifact\_bundles:read for API keys.
- `rubrkit\_export\_proof\_report`: Start an async proof report job with export storage enabled by default. Requires evals:run for API keys.
- `rubrkit\_read\_proof\_report`: Read one proof report. Requires artifact\_bundles:read for API keys.
- `rubrkit\_list\_golden\_cases`: List the golden cases for an artifact bundle via /api/v1/artifact-bundles/\{artifactBundleId\}/golden-cases. Requires artifact\_bundles:read \(or artifacts:pull\) for API keys.
- `rubrkit\_add\_golden\_case`: Add a golden case \(a real edge-case input with a confirmed-correct output\) to an artifact bundle via POST /api/v1/artifact-bundles/\{artifactBundleId\}/golden-cases. Requires artifact\_bundles:write for API keys.
- `rubrkit\_retire\_golden\_case`: Retire a golden case via DELETE /api/v1/golden-cases/\{goldenCaseId\}. Requires artifact\_bundles:write for API keys.
- `rubrkit\_create\_drift\_monitor`: Create a drift monitor pinned to a file version via POST /api/v1/artifact-bundles/\{artifactBundleId\}/drift-monitors. Requires artifact\_bundles:write for API keys.
- `rubrkit\_list\_drift\_monitors`: List the drift monitors for an artifact bundle via /api/v1/artifact-bundles/\{artifactBundleId\}/drift-monitors. Requires artifact\_bundles:read \(or artifacts:pull\) for API keys.
- `rubrkit\_read\_drift\_observations`: List the recorded observations for a drift monitor via /api/v1/drift-monitors/\{driftMonitorId\}/observations. Requires artifact\_bundles:read \(or artifacts:pull\) for API keys.
- `rubrkit\_run\_drift\_check`: Queue a drift check immediately instead of waiting for the monitor's schedule, via POST /api/v1/drift-monitors/\{driftMonitorId\}/check. The first check on a new monitor calibrates its baseline. Costs one audit per repeat. Requires artifact\_bundles:write for API keys.
- `rubrkit\_set\_drift\_monitor\_status`: Pause or resume a drift monitor via PATCH /api/v1/drift-monitors/\{driftMonitorId\}. Requires artifact\_bundles:write for API keys.
- `rubrkit\_record\_outcome`: Record a production outcome event \(input feature, metric, and/or label\) for an artifact bundle via POST /api/v1/artifact-bundles/\{artifactBundleId\}/outcomes. Requires artifact\_bundles:write for API keys.
- `rubrkit\_read\_input\_drift`: Compare recent production inputs against a prior reference window \(population stability index\) for an artifact bundle via GET /api/v1/artifact-bundles/\{artifactBundleId\}/drift/input. Requires artifact\_bundles:read \(or artifacts:pull\) for API keys.
- `rubrkit\_read\_validity\_drift`: Correlate rubric scores against recorded outcome metrics for an artifact bundle to check whether the rubric is still predictive via GET /api/v1/artifact-bundles/\{artifactBundleId\}/drift/validity. Requires artifact\_bundles:read \(or artifacts:pull\) for API keys.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html