MCP MeasureMCP Measure

index observed

rubrkit

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

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
79%
Naming quality
77%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (6)

  • LOWTool 'rubrkit_hard_delete_artifact_bundle' name length outside 3-30 rangein rubrkit_hard_delete_artifact_bundle
  • LOWTool 'rubrkit_estimate_deep_compaction' name length outside 3-30 rangein rubrkit_estimate_deep_compaction
  • LOWTool 'rubrkit_list_artifact_bundle_versions' name length outside 3-30 rangein rubrkit_list_artifact_bundle_versions
  • LOWTool 'rubrkit_restore_artifact_bundle_version' name length outside 3-30 rangein rubrkit_restore_artifact_bundle_version
  • LOWTool 'rubrkit_read_drift_observations' name length outside 3-30 rangein rubrkit_read_drift_observations
  • LOWTool 'rubrkit_set_drift_monitor_status' name length outside 3-30 rangein rubrkit_set_drift_monitor_status

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~4,317Tokens (tool definitions)
~682 BTypical response size
Significant attention impact (3.37% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "rubrkit": {
      "url": "https://www.rubrkit.com/api/v1/mcp"
    }
  }
}

Remote endpoints

https://www.rubrkit.com/api/v1/mcpstreamable-http

What it can do

Tool inventory

Tools (41)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢rubrkit_search_api_docs(query, limit)

Search the canonical docs/api Markdown guides and OpenAPI operation summaries.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "default": 8
    }
  },
  "required": [
    "query"
  ]
}
🟢rubrkit_read_api_doc(slugOrPath)

Read a docs/api Markdown guide or OpenAPI source by slug, file name, or docs/api path.

Input Schema

{
  "type": "object",
  "properties": {
    "slugOrPath": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "slugOrPath"
  ]
}
🟢rubrkit_read_openapi_contract

Read the canonical docs/api/openapi.yaml contract.

Input Schema

{
  "type": "object",
  "properties": {}
}
🟡rubrkit_create_artifact_bundle(name, description, customRubric, settings)

Create an artifact bundle through /api/v1/artifact-bundles. Requires artifact_bundles:write for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    },
    "description": {
      "type": [
        "string",
        "null"
      ],
      "maxLength": 2000
    },
    "customRubric": {
      "type": "object",
      "additionalProperties": true
    },
    "settings": {
      "type": "object",
      "additionalProperties": true
    }
  },
  "required": [
    "name"
  ]
}
🟢rubrkit_list_artifact_bundles(status, limit)

List artifact bundles through /api/v1/artifact-bundles. Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "enum": [
        "active",
        "archived",
        "all"
      ],
      "default": "active"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 100
    }
  }
}
🟢rubrkit_read_artifact_bundle(artifactBundleId)

Read artifact bundle details, files, and file tree. Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🔴rubrkit_delete_artifact_bundle(artifactBundleId)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🔴rubrkit_hard_delete_artifact_bundle(artifactBundleId)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟡rubrkit_upload_artifact_files(artifactBundleId, files)

Upload one or more text files into an artifact bundle. Requires files:write for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "files": {
      "type": "array",
      "minItems": 1,
      "items": {
        "type": "object",
        "required": [
          "path",
          "content"
        ],
        "properties": {
          "path": {
            "type": "string",
            "minLength": 1
          },
          "content": {
            "type": "string"
          },
          "mediaType": {
            "type": "string"
          },
          "artifactType": {
            "type": "string"
          },
          "message": {
            "type": "string",
            "maxLength": 500
          }
        }
      }
    }
  },
  "required": [
    "artifactBundleId",
    "files"
  ]
}
🟢rubrkit_list_artifact_files(artifactBundleId, limit)

List files in an artifact bundle. Requires files:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 200,
      "default": 200
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_read_artifact_file(artifactBundleId, fileId)

Read the latest file metadata and content. Requires files:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "fileId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId",
    "fileId"
  ]
}
🟡rubrkit_update_artifact_file(artifactBundleId, fileId, content, mediaType, message)

Write a new editable version for a file. Requires files:write for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "fileId": {
      "type": "string",
      "format": "uuid"
    },
    "content": {
      "type": "string"
    },
    "mediaType": {
      "type": "string"
    },
    "message": {
      "type": "string",
      "maxLength": 500
    }
  },
  "required": [
    "artifactBundleId",
    "fileId",
    "content"
  ]
}
⚪rubrkit_compact_artifact_file(artifactBundleId, fileId, mode, dryRun)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "fileId": {
      "type": "string",
      "format": "uuid"
    },
    "mode": {
      "type": "string",
      "enum": [
        "standard",
        "deep"
      ],
      "default": "standard"
    },
    "dryRun": {
      "type": "boolean",
      "default": false
    }
  },
  "required": [
    "artifactBundleId",
    "fileId"
  ]
}
⚪rubrkit_estimate_deep_compaction(artifactBundleId, fileId)

Estimate the credit cost of a deep compaction of one file before starting it. Requires compactions:run for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "fileId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId",
    "fileId"
  ]
}
🟡rubrkit_apply_deep_compaction(artifactBundleId, fileId, jobId)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "fileId": {
      "type": "string",
      "format": "uuid"
    },
    "jobId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId",
    "fileId",
    "jobId"
  ]
}
⚪rubrkit_start_audit(artifactBundleId, targetFileId, targetVersionNumber, artifactBundleVersionNumber, rubricKey, ...)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "targetFileId": {
      "type": "string",
      "format": "uuid"
    },
    "targetVersionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "artifactBundleVersionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "rubricKey": {
      "type": "string"
    },
    "artifactType": {
      "type": "string"
    },
    "customRequirements": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "modelTier": {
      "type": "string",
      "enum": [
        "cheap",
        "standard",
        "premium"
      ]
    },
    "reasoningEffort": {
      "type": "string",
      "enum": [
        "minimal",
        "low",
        "medium",
        "high"
      ]
    },
    "force": {
      "type": "boolean",
      "default": false
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_list_audits(artifactBundleId, limit)

List persisted audit history. Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 25
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_read_audit(artifactBundleId, auditRunId)

Read a single audit run. Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "auditRunId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId",
    "auditRunId"
  ]
}
⚪rubrkit_apply_audit_rewrite(artifactBundleId, auditRunId)

Apply a completed audit's AI rewrite to the bundle files (a new version per changed file). Requires audits:run for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "auditRunId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId",
    "auditRunId"
  ]
}
🟢rubrkit_poll_job(jobId)

Read async job progress. Requires jobs:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "jobId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "jobId"
  ]
}
🟢rubrkit_list_job_events(jobId, limit)

Read append-only job progress events. Requires jobs:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "jobId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 100
    }
  },
  "required": [
    "jobId"
  ]
}
🟢rubrkit_list_artifact_bundle_versions(artifactBundleId, limit)

List bundle-level version events. Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 100
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
⚪rubrkit_restore_artifact_bundle_version(artifactBundleId, versionNumber, message)

Restore files from a prior artifact-bundle version by creating new file versions. Requires artifact_bundles:write and files:write for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "versionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "message": {
      "type": "string",
      "maxLength": 500
    }
  },
  "required": [
    "artifactBundleId",
    "versionNumber"
  ]
}
🟢rubrkit_list_file_versions(artifactBundleId, fileId, limit)

List immutable versions for a file. Requires files:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "fileId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 100
    }
  },
  "required": [
    "artifactBundleId",
    "fileId"
  ]
}
⚪rubrkit_restore_file_version(artifactBundleId, fileId, versionNumber, message)

Restore a prior file version by creating a new version. Requires files:write for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "fileId": {
      "type": "string",
      "format": "uuid"
    },
    "versionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "message": {
      "type": "string",
      "maxLength": 500
    }
  },
  "required": [
    "artifactBundleId",
    "fileId",
    "versionNumber"
  ]
}
🟡rubrkit_run_evals(artifactBundleId, auditRunId, sourceFileVersionId, sourceFileId, sourceVersionNumber, ...)

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).

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "auditRunId": {
      "type": "string",
      "format": "uuid"
    },
    "sourceFileVersionId": {
      "type": "string",
      "format": "uuid"
    },
    "sourceFileId": {
      "type": "string",
      "format": "uuid"
    },
    "sourceVersionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "candidateFileVersionId": {
      "type": "string",
      "format": "uuid"
    },
    "candidateFileId": {
      "type": "string",
      "format": "uuid"
    },
    "candidateVersionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "rubricVersion": {
      "type": "string"
    },
    "maxCases": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    },
    "testCases": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "mode": {
      "type": "string",
      "enum": [
        "standard",
        "advanced"
      ]
    },
    "repeats": {
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "baselineVersionId": {
      "type": "string",
      "format": "uuid"
    },
    "candidateVersionId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_list_evals(artifactBundleId, limit)

List eval history. Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 25
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_read_eval(artifactBundleId, evalRunId)

Read one eval run, including the `stats` statistical verdict on advanced-mode runs (empty for standard runs). Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "evalRunId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId",
    "evalRunId"
  ]
}
⚪rubrkit_export_proof_report(artifactBundleId, evalRunId, auditRunId, sourceFileVersionId, sourceFileId, ...)

Start an async proof report job with export storage enabled by default. Requires evals:run for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "evalRunId": {
      "type": "string",
      "format": "uuid"
    },
    "auditRunId": {
      "type": "string",
      "format": "uuid"
    },
    "sourceFileVersionId": {
      "type": "string",
      "format": "uuid"
    },
    "sourceFileId": {
      "type": "string",
      "format": "uuid"
    },
    "sourceVersionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "candidateFileVersionId": {
      "type": "string",
      "format": "uuid"
    },
    "candidateFileId": {
      "type": "string",
      "format": "uuid"
    },
    "candidateVersionNumber": {
      "type": "integer",
      "minimum": 1
    },
    "rubricVersion": {
      "type": "string"
    },
    "includeExport": {
      "type": "boolean",
      "default": true
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_read_proof_report(artifactBundleId, proofReportId)

Read one proof report. Requires artifact_bundles:read for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "proofReportId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId",
    "proofReportId"
  ]
}
🟢rubrkit_list_golden_cases(artifactBundleId, status)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "status": {
      "type": [
        "string",
        "null"
      ],
      "enum": [
        "active",
        "retired",
        null
      ]
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟡rubrkit_add_golden_case(artifactBundleId, input, expectedOutput, criteria, origin, ...)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "input": {
      "type": "object"
    },
    "expectedOutput": {
      "type": "object"
    },
    "criteria": {
      "type": "object"
    },
    "origin": {
      "type": "string",
      "enum": [
        "audit",
        "human",
        "prod"
      ]
    },
    "originRef": {
      "type": "object"
    },
    "weight": {
      "type": "integer",
      "minimum": 1
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "artifactBundleId",
    "input"
  ]
}
🔴rubrkit_retire_golden_case(goldenCaseId)

Retire a golden case via DELETE /api/v1/golden-cases/{goldenCaseId}. Requires artifact_bundles:write for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "goldenCaseId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "goldenCaseId"
  ]
}
🟡rubrkit_create_drift_monitor(artifactBundleId, pinnedVersionId, cadence, repeats)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "pinnedVersionId": {
      "type": "string",
      "format": "uuid"
    },
    "cadence": {
      "type": "string"
    },
    "repeats": {
      "type": "integer",
      "minimum": 2,
      "maximum": 5
    }
  },
  "required": [
    "artifactBundleId",
    "pinnedVersionId"
  ]
}
🟢rubrkit_list_drift_monitors(artifactBundleId)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_read_drift_observations(driftMonitorId)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "driftMonitorId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "driftMonitorId"
  ]
}
🟡rubrkit_run_drift_check(driftMonitorId)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "driftMonitorId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "driftMonitorId"
  ]
}
🟡rubrkit_set_drift_monitor_status(driftMonitorId, status)

Pause or resume a drift monitor via PATCH /api/v1/drift-monitors/{driftMonitorId}. Requires artifact_bundles:write for API keys.

Input Schema

{
  "type": "object",
  "properties": {
    "driftMonitorId": {
      "type": "string",
      "format": "uuid"
    },
    "status": {
      "type": "string",
      "enum": [
        "active",
        "paused"
      ]
    }
  },
  "required": [
    "driftMonitorId",
    "status"
  ]
}
🟡rubrkit_record_outcome(artifactBundleId, artifactVersionId, inputHash, inputFeature, outcomeMetric, ...)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "artifactVersionId": {
      "type": "string",
      "format": "uuid"
    },
    "inputHash": {
      "type": "string"
    },
    "inputFeature": {
      "type": "number"
    },
    "outcomeMetric": {
      "type": "number"
    },
    "outcomeLabel": {
      "type": "string"
    },
    "occurredAt": {
      "type": "string",
      "format": "date-time"
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_read_input_drift(artifactBundleId, windowDays, binCount)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    },
    "windowDays": {
      "type": "integer",
      "minimum": 1
    },
    "binCount": {
      "type": "integer",
      "minimum": 1
    }
  },
  "required": [
    "artifactBundleId"
  ]
}
🟢rubrkit_read_validity_drift(artifactBundleId)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "artifactBundleId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "artifactBundleId"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded41 tools
verifiedversion not recorded41 tools
verifiedversion not recorded41 tools
verifiedversion not recorded41 tools
verifiedversion not recorded39 tools
verifiedversion not recorded41 tools