rubrkit
Server Details
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 41 tools
Most tools target distinct verb+resource combinations, but a few overlaps exist (e.g., read_artifact_bundle vs list_artifact_files; read_api_doc vs read_openapi_contract vs search_api_docs) that could cause occasional misselection.
All tools use the rubrkit_ prefix and a consistent snake_case verb_noun pattern, with no mixed conventions or capitalization styles.
With 41 tools, the set is far above the typical 3–15 range and feels heavily granular. Although the domain is complex, many operations could likely be consolidated into fewer higher-level tools.
Core CRUD/lifecycle coverage for bundles, files, versions, audits, evals, drift monitors, and golden cases is present. Minor gaps include listing proof reports/jobs/outcomes and updating drift monitor configurations.
Available Tools
41 toolsrubrkit_add_golden_caseAdd golden caseBInspect
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.
Inputs: input (required), artifactBundleId (required), tags, origin, +4 more.
rubrkit_apply_audit_rewriteApply audit rewriteBInspect
Apply a completed audit's AI rewrite to the bundle files (a new version per changed file). Requires audits:run for API keys.
Inputs: auditRunId (required), artifactBundleId (required).
rubrkit_apply_deep_compactionApply deep compactionAInspect
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.
Inputs: jobId (required), fileId (required), artifactBundleId (required).
rubrkit_compact_artifact_fileCompact artifact fileAInspect
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 never saves on its own: poll the returned job, then call rubrkit_apply_deep_compaction; requires compactions:run for API keys.
Inputs: fileId (required), artifactBundleId (required), mode, dryRun.
rubrkit_create_artifact_bundleCreate artifact bundleAInspect
Create an artifact bundle through /api/v1/artifact-bundles. Requires artifact_bundles:write for API keys.
Inputs: name (required), settings, description, customRubric.
rubrkit_create_drift_monitorCreate drift monitorBInspect
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.
Inputs: pinnedVersionId (required), artifactBundleId (required), cadence, repeats.
rubrkit_delete_artifact_bundleDelete artifact bundleAInspect
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.
Inputs: artifactBundleId (required).
rubrkit_estimate_deep_compactionEstimate deep compactionAInspect
Estimate the credit cost of a deep compaction of one file before starting it. Requires compactions:run for API keys.
Inputs: fileId (required), artifactBundleId (required).
rubrkit_export_proof_reportExport proof reportBInspect
Start an async proof report job with export storage enabled by default. Requires evals:run for API keys.
Inputs: artifactBundleId (required), evalRunId, auditRunId, sourceFileId, +7 more.
rubrkit_hard_delete_artifact_bundlePermanently delete artifact bundleAInspect
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.
Inputs: artifactBundleId (required).
rubrkit_list_artifact_bundlesList artifact bundlesAInspect
List artifact bundles through /api/v1/artifact-bundles. Requires artifact_bundles:read for API keys.
Inputs: limit, status.
rubrkit_list_artifact_bundle_versionsList artifact bundle versionsBInspect
List bundle-level version events. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId (required), limit.
rubrkit_list_artifact_filesList artifact filesCInspect
List files in an artifact bundle. Requires files:read for API keys.
Inputs: artifactBundleId (required), limit.
rubrkit_list_auditsList auditsBInspect
List persisted audit history. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId (required), limit.
rubrkit_list_drift_monitorsList drift monitorsBInspect
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.
Inputs: artifactBundleId (required).
rubrkit_list_evalsList evalsCInspect
List eval history. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId (required), limit.
rubrkit_list_file_versionsList file versionsCInspect
List immutable versions for a file. Requires files:read for API keys.
Inputs: fileId (required), artifactBundleId (required), limit.
rubrkit_list_golden_casesList golden casesCInspect
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.
Inputs: artifactBundleId (required), status.
rubrkit_list_job_eventsList job eventsCInspect
Read append-only job progress events. Requires jobs:read for API keys.
Inputs: jobId (required), limit.
rubrkit_poll_jobPoll job progressCInspect
Read async job progress. Requires jobs:read for API keys.
Inputs: jobId (required).
rubrkit_read_api_docRead Rubrkit API docCInspect
Read a docs/api Markdown guide or OpenAPI source by slug, file name, or docs/api path.
Inputs: slugOrPath (required).
rubrkit_read_artifact_bundleRead artifact bundleCInspect
Read artifact bundle details, files, and file tree. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId (required).
rubrkit_read_artifact_fileRead artifact fileCInspect
Read the latest file metadata and content. Requires files:read for API keys.
Inputs: fileId (required), artifactBundleId (required).
rubrkit_read_auditRead auditAInspect
Read a single audit run. Requires artifact_bundles:read for API keys.
Inputs: auditRunId (required), artifactBundleId (required).
rubrkit_read_drift_observationsRead drift observationsBInspect
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.
Inputs: driftMonitorId (required).
rubrkit_read_evalRead evalAInspect
Read one eval run, including the stats statistical verdict on advanced-mode runs (empty for standard runs). Requires artifact_bundles:read for API keys.
Inputs: evalRunId (required), artifactBundleId (required).
rubrkit_read_input_driftRead input driftBInspect
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.
Inputs: artifactBundleId (required), binCount, windowDays.
rubrkit_read_openapi_contractRead Rubrkit OpenAPI contractAInspect
Read the canonical docs/api/openapi.yaml contract.
Inputs: no named parameters.
rubrkit_read_proof_reportRead proof reportCInspect
Read one proof report. Requires artifact_bundles:read for API keys.
Inputs: proofReportId (required), artifactBundleId (required).
rubrkit_read_validity_driftRead validity driftAInspect
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.
Inputs: artifactBundleId (required).
rubrkit_record_outcomeRecord outcomeBInspect
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.
Inputs: artifactBundleId (required), inputHash, occurredAt, inputFeature, +3 more.
rubrkit_restore_artifact_bundle_versionRestore artifact bundle versionBInspect
Restore files from a prior artifact-bundle version by creating new file versions. Requires artifact_bundles:write and files:write for API keys.
Inputs: versionNumber (required), artifactBundleId (required), message.
rubrkit_restore_file_versionRestore file versionBInspect
Restore a prior file version by creating a new version. Requires files:write for API keys.
Inputs: fileId (required), versionNumber (required), artifactBundleId (required), message.
rubrkit_retire_golden_caseRetire golden caseAInspect
Retire a golden case via DELETE /api/v1/golden-cases/{goldenCaseId}. Requires artifact_bundles:write for API keys.
Inputs: goldenCaseId (required).
rubrkit_run_drift_checkRun drift check nowAInspect
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.
Inputs: driftMonitorId (required).
rubrkit_run_evalsRun evalsAInspect
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).
Inputs: artifactBundleId (required), mode, repeats, maxCases, +11 more.
rubrkit_search_api_docsSearch Rubrkit API docsCInspect
Search the canonical docs/api Markdown guides and OpenAPI operation summaries.
Inputs: query (required), limit.
rubrkit_set_drift_monitor_statusSet drift monitor statusBInspect
Pause or resume a drift monitor via PATCH /api/v1/drift-monitors/{driftMonitorId}. Requires artifact_bundles:write for API keys.
Inputs: status (required), driftMonitorId (required).
rubrkit_start_auditStart auditAInspect
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.
Inputs: artifactBundleId (required), force, modelTier, rubricKey, +6 more.
rubrkit_update_artifact_fileUpdate artifact fileCInspect
Write a new editable version for a file. Requires files:write for API keys.
Inputs: fileId (required), content (required), artifactBundleId (required), message, +1 more.
rubrkit_upload_artifact_filesUpload artifact filesCInspect
Upload one or more text files into an artifact bundle. Requires files:write for API keys.
Inputs: files (required), artifactBundleId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Independent AI-governance measurement MCP. Free reads + x402 evidence. Measurement not cert.
Remote MCP tools for 3-vendor AI workflow diagnostics, HAR sandboxes, 50v audits, and rubrics.
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides AI governance controls as MCP tools for safety screening, risk classification, and red teaming of AI systems, returning structured governance reports.32Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP server for AI compliance auditing. Scores agent outputs for hallucination liability under the EU AI Act, issues verifiable compliance stamps, and tracks audit history by agent.MIT
- AlicenseNot gradedqualityBmaintenanceScores AI outputs for faithfulness, relevancy, and hallucination inside any MCP client, with custom metrics, golden sets, and run history with dashboards.Apache 2.0

HumanJudgeofficial
AlicenseNot gradedqualityCmaintenanceHuman-evaluation infrastructure for AI quality. 25,000+ blind human reviews by 200+ verified reviewers across 58 AI models — query the data via five MCP tools (get_model_scores, compare_models, get_flags, check_content, get_latest).2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.