Connect Rubrkit and your agent gets 41 tools, among them rubrkit_add_golden_case, rubrkit_apply_audit_rewrite, rubrkit_convert_to_rubr_flow. It answers at https://www.rubrkit.com/api/v1/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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. Inputs: artifactBundleId, input, expectedOutput, criteria, origin, originRef |
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. Inputs: artifactBundleId, auditRunId |
rubrkit_convert_to_rubr_flow | Start an async rubr_flow conversion job. Requires rubr_flow:convert for API keys. Inputs: artifactBundleId, targetFileId, targetVersionNumber, artifactBundleVersionNumber, outputPath, modelTier |
rubrkit_create_artifact_bundle | Create an artifact bundle through /api/v1/artifact-bundles. Requires artifact_bundles:write for API keys. Inputs: name, description, customRubric, settings |
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. Inputs: artifactBundleId, pinnedVersionId, cadence, repeats |
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. Inputs: artifactBundleId |
rubrkit_export_proof_report | Start an async proof report job with export storage enabled by default. Requires evals:run for API keys. Inputs: artifactBundleId, evalRunId, auditRunId, sourceFileVersionId, sourceFileId, sourceVersionNumber |
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. R Inputs: artifactBundleId |
rubrkit_list_artifact_bundle_versions | List bundle-level version events. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId, limit |
rubrkit_list_artifact_bundles | List artifact bundles through /api/v1/artifact-bundles. Requires artifact_bundles:read for API keys. Inputs: status, limit |
rubrkit_list_artifact_files | List files in an artifact bundle. Requires files:read for API keys. Inputs: artifactBundleId, limit |
rubrkit_list_audits | List persisted audit history. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId, limit |
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. Inputs: artifactBundleId |
rubrkit_list_evals | List eval history. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId, limit |
rubrkit_list_file_versions | List immutable versions for a file. Requires files:read for API keys. Inputs: artifactBundleId, fileId, limit |
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. Inputs: artifactBundleId, status |
rubrkit_list_job_events | Read append-only job progress events. Requires jobs:read for API keys. Inputs: jobId, limit |
rubrkit_list_rubr_flow_conversions | List conversion history. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId, limit |
rubrkit_poll_job | Read async job progress. Requires jobs:read for API keys. Inputs: jobId |
rubrkit_read_api_doc | Read a docs/api Markdown guide or OpenAPI source by slug, file name, or docs/api path. Inputs: slugOrPath |
rubrkit_read_artifact_bundle | Read artifact bundle details, files, and file tree. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId |
rubrkit_read_artifact_file | Read the latest file metadata and content. Requires files:read for API keys. Inputs: artifactBundleId, fileId |
rubrkit_read_audit | Read a single audit run. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId, auditRunId |
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. Inputs: driftMonitorId |
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. Inputs: artifactBundleId, evalRunId |
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 AP Inputs: artifactBundleId, windowDays, binCount |
rubrkit_read_openapi_contract | Read the canonical docs/api/openapi.yaml contract. |
rubrkit_read_proof_report | Read one proof report. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId, proofReportId |
rubrkit_read_rubr_flow_conversion | Read one conversion report. Requires artifact_bundles:read for API keys. Inputs: artifactBundleId, conversionId |
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 Inputs: artifactBundleId |
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. Inputs: artifactBundleId, artifactVersionId, inputHash, inputFeature, outcomeMetric, outcomeLabel |
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. Inputs: artifactBundleId, versionNumber, message |
rubrkit_restore_file_version | Restore a prior file version by creating a new version. Requires files:write for API keys. Inputs: artifactBundleId, fileId, versionNumber, message |
rubrkit_retire_golden_case | Retire a golden case via DELETE /api/v1/golden-cases/{goldenCaseId}. Requires artifact_bundles:write for API keys. Inputs: goldenCaseId |
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_b Inputs: driftMonitorId |
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). Inputs: artifactBundleId, auditRunId, sourceFileVersionId, sourceFileId, sourceVersionNumber, candidateFileVersionId |
rubrkit_search_api_docs | Search the canonical docs/api Markdown guides and OpenAPI operation summaries. Inputs: query, limit |
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. Inputs: driftMonitorId, status |
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. Inputs: artifactBundleId, targetFileId, targetVersionNumber, artifactBundleVersionNumber, rubricKey, artifactType |
rubrkit_update_artifact_file | Write a new editable version for a file. Requires files:write for API keys. Inputs: artifactBundleId, fileId, content, mediaType, message |
rubrkit_upload_artifact_files
Every block below points at https://www.rubrkit.com/api/v1/mcp. Pick your client and copy.
claude mcp add --transport http rubrkit https://www.rubrkit.com/api/v1/mcp
{
"mcpServers": {
"rubrkit": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://www.rubrkit.com/api/v1/mcp"]
}
}
}{
"mcpServers": {
"rubrkit": {
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}{
"servers": {
"rubrkit": {
"type": "http",
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}{
"context_servers": {
"rubrkit": {
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}{
"mcpServers": {
"rubrkit": {
"serverUrl": "https://www.rubrkit.com/api/v1/mcp"
}
}
}{
"mcpServers": {
"rubrkit": {
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}name: Rubrkit
version: 0.0.1
schema: v1
mcpServers:
- name: Rubrkit
type: streamable-http
url: https://www.rubrkit.com/api/v1/mcp{
"mcpServers": {
"rubrkit": {
"httpUrl": "https://www.rubrkit.com/api/v1/mcp"
}
}
}{
"mcpServers": {
"rubrkit": {
"type": "http",
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}{
"mcpServers": {
"rubrkit": {
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fwww.rubrkit.com%2Fapi%2Fv1%2Fmcp&type=streamable_http&id=rubrkit&name=Rubrkit
It answered our last check on 18 October 2026 in 240 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by rubrkit.com and served from www.rubrkit.com, the vendor's own domain: https://www.rubrkit.com/api/v1/mcp.
41, as returned by the server's own tools/list on 31 August 2026: rubrkit_add_golden_case, rubrkit_apply_audit_rewrite, rubrkit_convert_to_rubr_flow, rubrkit_create_artifact_bundle, rubrkit_create_drift_monitor, rubrkit_delete_artifact_bundle, rubrkit_export_proof_report, rubrkit_hard_delete_artifact_bundle, and 33 more.
It answered our last check on 18 October 2026 in 240 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://www.rubrkit.com/api/v1/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.rubrkit. Endpoint host: www.rubrkit.com. ARD identifier: urn:air:com.rubrkit:mcp:rubrkit.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.