API Tools
rubrkit.com
Provides functions to search and read API documentation and manage artifact bundles.
ENDPOINT 1
https://www.rubrkit.com/api/v1/mcp
MCP server metadata
- Name
- rubrkit
- Version
- 0.1.0
Rubrkit MCP exposes public API docs and authenticated product tools backed by the same /api/v1 controllers, scopes, limits, credits, and ownership checks as REST.
Known tools 41
rubrkit_search_api_docsSearch the canonical docs/api Markdown guides and OpenAPI operation summaries.
Inferred read-onlyrubrkit_read_api_docRead a docs/api Markdown guide or OpenAPI source by slug, file name, or docs/api path.
Inferred read-onlyrubrkit_create_artifact_bundleCreate an artifact bundle through /api/v1/artifact-bundles.
Potential side effectsrubrkit_list_artifact_bundlesList artifact bundles through /api/v1/artifact-bundles.
Inferred read-onlyrubrkit_delete_artifact_bundleArchive an artifact bundle (soft delete) through DELETE /api/v1/artifact-bundles/{artifactBundleId}.
Potential side effectsrubrkit_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.
Potential side effectsrubrkit_upload_artifact_filesUpload one or more text files into an artifact bundle.
Potential side effectsrubrkit_apply_audit_rewriteApply a completed audit's AI rewrite to the bundle files (a new version per changed file).
Inferred read-onlyrubrkit_restore_artifact_bundle_versionRestore files from a prior artifact-bundle version by creating new file versions.
Inferred read-onlyrubrkit_restore_file_versionRestore a prior file version by creating a new version.
Inferred read-onlyrubrkit_read_evalRead one eval run, including the `stats` statistical verdict on advanced-mode runs (empty for standard runs).
Potential side effectsrubrkit_export_proof_reportStart an async proof report job with export storage enabled by default.
Inferred read-onlyrubrkit_list_golden_casesList the golden cases for an artifact bundle via /api/v1/artifact-bundles/{artifactBundleId}/golden-cases.
Inferred read-onlyrubrkit_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.
Potential side effectsrubrkit_retire_golden_caseRetire a golden case via DELETE /api/v1/golden-cases/{goldenCaseId}.
Potential side effectsrubrkit_create_drift_monitorCreate a drift monitor pinned to a file version via POST /api/v1/artifact-bundles/{artifactBundleId}/drift-monitors.
Potential side effectsrubrkit_list_drift_monitorsList the drift monitors for an artifact bundle via /api/v1/artifact-bundles/{artifactBundleId}/drift-monitors.
Inferred read-onlyrubrkit_read_drift_observationsList the recorded observations for a drift monitor via /api/v1/drift-monitors/{driftMonitorId}/observations.
Inferred read-onlyrubrkit_run_drift_checkQueue a drift check immediately instead of waiting for the monitor's schedule, via POST /api/v1/drift-monitors/{driftMonitorId}/check.
Potential side effectsrubrkit_set_drift_monitor_statusPause or resume a drift monitor via PATCH /api/v1/drift-monitors/{driftMonitorId}.
Inferred read-onlyrubrkit_record_outcomeRecord a production outcome event (input feature, metric, and/or label) for an artifact bundle via POST /api/v1/artifact-bundles/{artifactBundleId}/outcomes.
Potential side effectsrubrkit_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.
Inferred read-onlyrubrkit_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.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.rubrkit]
url = "https://www.rubrkit.com/api/v1/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"rubrkit": {
"type": "http",
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: rubrkit
Remote MCP URL: https://www.rubrkit.com/api/v1/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"rubrkit": {
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"rubrkit": {
"type": "http",
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "rubrkit",
"transport": "streamable-http",
"url": "https://www.rubrkit.com/api/v1/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.