Rubrkit

com.rubrkitPublished by rubrkit.comOfficial publisherv1.0.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableDeveloper Tools Data & Analytics AI & ML

Server details

Identifier: com.rubrkit/rubrkit
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to rubrkit.com, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.rubrkit%2Frubrkit.svg)](https://sourceweft.com/mcp/com.rubrkit%2Frubrkit?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Lets an assistant manage artifact bundles, run rubric audits and evals, and produce proof reports for AI/LLM output.

What you can do: Rubrkit exposes a remote API for evaluating AI output. Assistants can search and read API docs and the OpenAPI contract, create and manage artifact bundles, upload, read, update and version text files, and run asynchronous audits, evals and proof reports. It also supports golden cases, drift monitors with observations and input-drift comparison, job polling, and compaction of markdown or text prompts.
When to use it: Use it when you want an assistant to organize prompts or model outputs into bundles and then audit, evaluate, version, or monitor them for drift. It suits teams that need repeatable eval runs, A/B comparisons, or exported proof reports rather than one-off checks.
Requirements: A remote streamable HTTP endpoint at the provider's site; no local package or environment variables are declared. API keys are needed for most operations, with scopes such as artifact_bundles:read, artifact_bundles:write, files:read, files:write, audits:run, evals:run, compactions:run and jobs:read. Network access to the provider is required.

Before you install

Several tools write or delete data: bundles can be archived or permanently deleted, files and versions overwritten or restored, and audit rewrites applied. Deep compaction, audits, evals and drift checks consume credits, and drift checks cost one audit per repeat. Most tools require a scoped API key, so grant only the scopes needed.

Installation

In SourceWeft

Open Rubrkit in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.rubrkit%2Frubrkit/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

README

This repository has no README.

Tools

rubrkit_search_api_docs

Search Rubrkit API docs

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

Parameterslimitqueryrequired

rubrkit_read_api_doc

Read Rubrkit API doc

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

ParametersslugOrPathrequired

rubrkit_read_openapi_contract

Read Rubrkit OpenAPI contract

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

Takes no parameters.

rubrkit_create_artifact_bundle

Create artifact bundle

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

ParametersnamerequiredsettingsdescriptioncustomRubric

rubrkit_list_artifact_bundles

List artifact bundles

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

Parameterslimitstatus

rubrkit_read_artifact_bundle

Read artifact bundle

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

ParametersartifactBundleIdrequired

rubrkit_delete_artifact_bundle

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.

ParametersartifactBundleIdrequired

rubrkit_hard_delete_artifact_bundle

Permanently 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. Requires artifact_bundles:write for API keys.

ParametersartifactBundleIdrequired

rubrkit_upload_artifact_files

Upload artifact files

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

ParametersfilesrequiredartifactBundleIdrequired

rubrkit_list_artifact_files

List artifact files

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

ParameterslimitartifactBundleIdrequired

rubrkit_read_artifact_file

Read artifact file

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

ParametersfileIdrequiredartifactBundleIdrequired

rubrkit_update_artifact_file

Update artifact file

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

ParametersfileIdrequiredcontentrequiredmessagemediaTypeartifactBundleIdrequired

rubrkit_compact_artifact_file

Compact artifact file

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.

ParametersmodedryRunfileIdrequiredartifactBundleIdrequired

rubrkit_estimate_deep_compaction

Estimate deep compaction

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

ParametersfileIdrequiredartifactBundleIdrequired

rubrkit_apply_deep_compaction

Apply deep compaction

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.

ParametersjobIdrequiredfileIdrequiredartifactBundleIdrequired

rubrkit_start_audit

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.

ParametersforcemodelTierrubricKeyartifactTypetargetFileIdreasoningEffortartifactBundleIdrequiredcustomRequirementstargetVersionNumberartifactBundleVersionNumber

rubrkit_list_audits

List audits

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

ParameterslimitartifactBundleIdrequired

rubrkit_read_audit

Read audit

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

ParametersauditRunIdrequiredartifactBundleIdrequired

rubrkit_apply_audit_rewrite

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.

ParametersauditRunIdrequiredartifactBundleIdrequired

rubrkit_poll_job

Poll job progress

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

ParametersjobIdrequired

rubrkit_list_job_events

List job events

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

ParametersjobIdrequiredlimit

rubrkit_list_artifact_bundle_versions

List artifact bundle versions

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

ParameterslimitartifactBundleIdrequired

rubrkit_restore_artifact_bundle_version

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.

ParametersmessageversionNumberrequiredartifactBundleIdrequired

rubrkit_list_file_versions

List file versions

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

ParameterslimitfileIdrequiredartifactBundleIdrequired

rubrkit_restore_file_version

Restore file version

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

ParametersfileIdrequiredmessageversionNumberrequiredartifactBundleIdrequired

rubrkit_run_evals

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).

ParametersmoderepeatsmaxCasestestCasesauditRunIdsourceFileIdrubricVersioncandidateFileIdartifactBundleIdrequiredbaselineVersionIdcandidateVersionIdsourceFileVersionId+3 more

rubrkit_list_evals

List evals

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

ParameterslimitartifactBundleIdrequired

rubrkit_read_eval

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.

ParametersevalRunIdrequiredartifactBundleIdrequired

rubrkit_export_proof_report

Export proof report

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

ParametersevalRunIdauditRunIdsourceFileIdincludeExportrubricVersioncandidateFileIdartifactBundleIdrequiredsourceFileVersionIdsourceVersionNumbercandidateFileVersionIdcandidateVersionNumber

rubrkit_read_proof_report

Read proof report

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

ParametersproofReportIdrequiredartifactBundleIdrequired

rubrkit_list_golden_cases

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.

ParametersstatusartifactBundleIdrequired

rubrkit_add_golden_case

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.

ParameterstagsinputrequiredoriginweightcriteriaoriginRefexpectedOutputartifactBundleIdrequired

rubrkit_retire_golden_case

Retire golden case

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

ParametersgoldenCaseIdrequired

rubrkit_create_drift_monitor

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.

ParameterscadencerepeatspinnedVersionIdrequiredartifactBundleIdrequired

rubrkit_list_drift_monitors

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.

ParametersartifactBundleIdrequired

rubrkit_read_drift_observations

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.

ParametersdriftMonitorIdrequired

rubrkit_run_drift_check

Run drift check now

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.

ParametersdriftMonitorIdrequired

rubrkit_set_drift_monitor_status

Set drift monitor status

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

ParametersstatusrequireddriftMonitorIdrequired

rubrkit_record_outcome

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.

ParametersinputHashoccurredAtinputFeatureoutcomeLabeloutcomeMetricartifactBundleIdrequiredartifactVersionId

rubrkit_read_input_drift

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 API keys.

ParametersbinCountwindowDaysartifactBundleIdrequired

rubrkit_read_validity_drift

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:pull) for API keys.

ParametersartifactBundleIdrequired

Version history

v1.0.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.