Index / MCP servers / Rubrkit

Rubrkit MCP server

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.

Status
Answering
Tools
41
Official
yes, served from rubrkit.com
Reliability
10 of 10 checks
Response time
240 ms
Transport
streamable HTTP
Last checked
18 October 2026

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

Description as the publisher wrote it.

The 41 tools Rubrkit offers

ToolWhat it does
rubrkit_add_golden_caseAdd 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_rewriteApply 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_flowStart an async rubr_flow conversion job. Requires rubr_flow:convert for API keys.
Inputs: artifactBundleId, targetFileId, targetVersionNumber, artifactBundleVersionNumber, outputPath, modelTier
rubrkit_create_artifact_bundleCreate an artifact bundle through /api/v1/artifact-bundles. Requires artifact_bundles:write for API keys.
Inputs: name, description, customRubric, settings
rubrkit_create_drift_monitorCreate 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_bundleArchive 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_reportStart 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_bundlePermanently 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_versionsList bundle-level version events. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId, limit
rubrkit_list_artifact_bundlesList artifact bundles through /api/v1/artifact-bundles. Requires artifact_bundles:read for API keys.
Inputs: status, limit
rubrkit_list_artifact_filesList files in an artifact bundle. Requires files:read for API keys.
Inputs: artifactBundleId, limit
rubrkit_list_auditsList persisted audit history. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId, limit
rubrkit_list_drift_monitorsList 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_evalsList eval history. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId, limit
rubrkit_list_file_versionsList immutable versions for a file. Requires files:read for API keys.
Inputs: artifactBundleId, fileId, limit
rubrkit_list_golden_casesList 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_eventsRead append-only job progress events. Requires jobs:read for API keys.
Inputs: jobId, limit
rubrkit_list_rubr_flow_conversionsList conversion history. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId, limit
rubrkit_poll_jobRead async job progress. Requires jobs:read for API keys.
Inputs: jobId
rubrkit_read_api_docRead a docs/api Markdown guide or OpenAPI source by slug, file name, or docs/api path.
Inputs: slugOrPath
rubrkit_read_artifact_bundleRead artifact bundle details, files, and file tree. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId
rubrkit_read_artifact_fileRead the latest file metadata and content. Requires files:read for API keys.
Inputs: artifactBundleId, fileId
rubrkit_read_auditRead a single audit run. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId, auditRunId
rubrkit_read_drift_observationsList 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_evalRead 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_driftCompare 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_contractRead the canonical docs/api/openapi.yaml contract.
rubrkit_read_proof_reportRead one proof report. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId, proofReportId
rubrkit_read_rubr_flow_conversionRead one conversion report. Requires artifact_bundles:read for API keys.
Inputs: artifactBundleId, conversionId
rubrkit_read_validity_driftCorrelate 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_outcomeRecord 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_versionRestore 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_versionRestore a prior file version by creating a new version. Requires files:write for API keys.
Inputs: artifactBundleId, fileId, versionNumber, message
rubrkit_retire_golden_caseRetire a golden case via DELETE /api/v1/golden-cases/{goldenCaseId}. Requires artifact_bundles:write for API keys.
Inputs: goldenCaseId
rubrkit_run_drift_checkQueue 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_evalsStart 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_docsSearch the canonical docs/api Markdown guides and OpenAPI operation summaries.
Inputs: query, limit
rubrkit_set_drift_monitor_statusPause or resume a drift monitor via PATCH /api/v1/drift-monitors/{driftMonitorId}. Requires artifact_bundles:write for API keys.
Inputs: driftMonitorId, status
rubrkit_start_auditStart 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_fileWrite a new editable version for a file. Requires files:write for API keys.
Inputs: artifactBundleId, fileId, content, mediaType, message
1 more tools

rubrkit_upload_artifact_files

Add Rubrkit to your AI client

Every block below points at https://www.rubrkit.com/api/v1/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http rubrkit https://www.rubrkit.com/api/v1/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "rubrkit": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://www.rubrkit.com/api/v1/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "rubrkit": {
      "url": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "rubrkit": {
      "type": "http",
      "url": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "rubrkit": {
      "url": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "rubrkit": {
      "serverUrl": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "rubrkit": {
      "url": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Rubrkit
version: 0.0.1
schema: v1
mcpServers:
  - name: Rubrkit
    type: streamable-http
    url: https://www.rubrkit.com/api/v1/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "rubrkit": {
      "httpUrl": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "rubrkit": {
      "type": "http",
      "url": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "rubrkit": {
      "url": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fwww.rubrkit.com%2Fapi%2Fv1%2Fmcp&type=streamable_http&id=rubrkit&name=Rubrkit

Is Rubrkit up right now?

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.

MCP servers similar to Rubrkit

Questions about Rubrkit

Is there an official Rubrkit MCP server?

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.

How many tools does Rubrkit have?

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.

Is Rubrkit down?

It answered our last check on 18 October 2026 in 240 ms. Over 10 checks since 5 September 2026 it answered 10.

How do I add Rubrkit to Cursor?

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.

Does Rubrkit need an API key?

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.

Where this comes from

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.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.