Loading…
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 6 days ago
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The rubrkit MCP server exposes 41 tools, focused primarily on filesystem, web, and developer capabilities. Its published description reads: "MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates rubrkit F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check rubrkit's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add rubrkit to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://www.rubrkit.com/api/v1/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search the canonical docs/api Markdown guides and OpenAPI operation summaries.
Read a docs/api Markdown guide or OpenAPI source by slug, file name, or docs/api path.
Read the canonical docs/api/openapi.yaml contract.
Create an artifact bundle through /api/v1/artifact-bundles. Requires artifact_bundles:write for API keys.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: rubrkit_upload_artifact_files
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
files:write for API keys. {"type":"object","required":["artifactBundleIdRecommendationRemove side-channel parameters; constrain tool inputs.
tool: rubrkit_read_rubr_flow_conversion
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
undles:read for API keys. {"type":"object","required":["artifactBundleIdRecommendationRemove side-channel parameters; constrain tool inputs.
tool: rubrkit_restore_artifact_bundle_version
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
rtifact_bundles:write and files:write for API keys. {"type":"object","required"RecommendationAnnotate destructive tools and require human approval.
tool: rubrkit_export_proof_report
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
s evals:run for API keys. {"type":"object","required":["artifactBundleIdRecommendationRemove side-channel parameters; constrain tool inputs.
tool: rubrkit_read_proof_report
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
undles:read for API keys. {"type":"object","required":["artifactBundleIdRecommendationRemove side-channel parameters; constrain tool inputs.
tool: rubrkit_add_golden_case
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ndles:write for API keys. {"type":"object","required":["artifactBundleIdRecommendationRemove side-channel parameters; constrain tool inputs.
tool: rubrkit_create_drift_monitor
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ndles:write for API keys. {"type":"object","required":["artifactBundleIdRecommendationRemove side-channel parameters; constrain tool inputs.
tool: rubrkit_run_drift_check
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ndles:write for API keys. {"type":"object","required":["driftMonitorId"]RecommendationRemove side-channel parameters; constrain tool inputs.
tool: rubrkit_run_drift_check
A tool description tries to alter the model’s use of another tool.
onitor's schedule, via POST /api/v1/drift-monitors/{driftMonitorId}/check.RecommendationDescriptions must describe only their own tool.
tool: rubrkit_record_outcome
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ndles:write for API keys. {"type":"object","required":["artifactBundleIdRecommendationRemove side-channel parameters; constrain tool inputs.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: rubrkit_create_artifact_bundle
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_create_artifact_bundle"RecommendationScope tools to the minimum needed.
tool: rubrkit_delete_artifact_bundle
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_delete_artifact_bundle"RecommendationScope tools to the minimum needed.
tool: rubrkit_hard_delete_artifact_bundle
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_hard_delete_artifact_bundle"RecommendationScope tools to the minimum needed.
tool: rubrkit_upload_artifact_files
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_upload_artifact_files"RecommendationScope tools to the minimum needed.
tool: rubrkit_list_artifact_files
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
_artifact_files List artifact files List files in an artifact bundle. Requires files:read forRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: rubrkit_read_artifact_file
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
d_artifact_file Read artifact file Read the latest file metadata and content. RequRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: rubrkit_update_artifact_file
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_update_artifact_file"RecommendationScope tools to the minimum needed.
tool: rubrkit_restore_artifact_bundle_version
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_restore_artifact_bundle_version"RecommendationScope tools to the minimum needed.
tool: rubrkit_restore_artifact_bundle_version
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
rtifact_bundles:write and files:write for API keys. {"type":"object","required"RecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: rubrkit_list_file_versions
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
t_file_versions List file versions List immutable versions for a file. ReRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: rubrkit_restore_file_version
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_restore_file_version"RecommendationScope tools to the minimum needed.
tool: rubrkit_run_evals
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_run_evals"RecommendationScope tools to the minimum needed.
tool: rubrkit_add_golden_case
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_add_golden_case"RecommendationScope tools to the minimum needed.
tool: rubrkit_retire_golden_case
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_retire_golden_case"RecommendationScope tools to the minimum needed.
tool: rubrkit_create_drift_monitor
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_create_drift_monitor"RecommendationScope tools to the minimum needed.
tool: rubrkit_run_drift_check
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_run_drift_check"RecommendationScope tools to the minimum needed.
tool: rubrkit_set_drift_monitor_status
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_set_drift_monitor_status"RecommendationScope tools to the minimum needed.
tool: rubrkit_record_outcome
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "rubrkit_record_outcome"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
List artifact bundles through /api/v1/artifact-bundles. Requires artifact_bundles:read for API keys.
Read artifact bundle details, files, and file tree. Requires artifact_bundles:read for API keys.
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 a
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
Upload one or more text files into an artifact bundle. Requires files:write for API keys.
List files in an artifact bundle. Requires files:read for API keys.
Read the latest file metadata and content. Requires files:read for API keys.
Write a new editable version for a file. Requires files:write for API keys.
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). Re
List persisted audit history. Requires artifact_bundles:read for API keys.
Read a single audit run. Requires artifact_bundles:read for API keys.
Apply a completed audit's AI rewrite to the bundle files (a new version per changed file). Requires audits:run for API keys.
Start an async rubr_flow conversion job. Requires rubr_flow:convert for API keys.
List conversion history. Requires artifact_bundles:read for API keys.
Read one conversion report. Requires artifact_bundles:read for API keys.
Read async job progress. Requires jobs:read for API keys.
Read append-only job progress events. Requires jobs:read for API keys.
List bundle-level version events. Requires artifact_bundles:read for API keys.
Restore files from a prior artifact-bundle version by creating new file versions. Requires artifact_bundles:write and files:write for API keys.
List immutable versions for a file. Requires files:read for API keys.
Restore a prior file version by creating a new version. Requires files:write for API keys.
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).
List eval history. Requires artifact_bundles:read for API keys.
Read one eval run, including the `stats` statistical verdict on advanced-mode runs (empty for standard runs). Requires artifact_bundles:read for API keys.
Start an async proof report job with export storage enabled by default. Requires evals:run for API keys.
Read one proof report. Requires artifact_bundles:read for API keys.
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.
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
Retire a golden case via DELETE /api/v1/golden-cases/{goldenCaseId}. Requires artifact_bundles:write for API keys.
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.
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.
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.
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 o
Pause or resume a drift monitor via PATCH /api/v1/drift-monitors/{driftMonitorId}. Requires artifact_bundles:write for API keys.
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 ke
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
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. Requ