mcp-registry/com.rubrkit/rubrkit · v0.1.0
As of 2026-10-25 23:17 UTC, the Rubrkit MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Claude Code
claude mcp add --transport http rubrkit-mcp-server https://www.rubrkit.com/api/v1/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"rubrkit-mcp-server": {
"type": "http",
"url": "https://www.rubrkit.com/api/v1/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
41 of 41 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
41 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
126 parameter(s) across 40 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
6 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
In the last 30 days: 1 tool(s) removed and 1 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 40 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fcom.rubrkit%2Frubrkit/fixes
{
"name": "rubrkit_add_golden_case",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"artifactBundleId",
"input"
],
"properties": {
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"input": {
"type": "object"
},
"origin": {
"enum": [
"audit",
"human",
"prod"
],
"type": "string"
},
"weight": {
"type": "integer",
"minimum": 1
},
"criteria": {
"type": "object"
},
"originRef": {
"type": "object"
},
"expectedOutput": {
"type": "object"
},
"artifactBundleId": {
"type": "string",
"format": "uuid"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
},
"title": "Add golden case"
}{
"name": "rubrkit_create_artifact_bundle",
"description": "Create an artifact bundle through /api/v1/artifact-bundles. Requires artifact_bundles:write for API keys.",
"inputSchema": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"maxLength": 120,
"minLength": 1
},
"settings": {
"type": "object",
"additionalProperties": true
},
"description": {
"type": [
"string",
"null"
],
"maxLength": 2000
},
"customRubric": {
"type": "object",
"additionalProperties": true
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
},
"title": "Create artifact bundle"
}{
"name": "rubrkit_create_drift_monitor",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"artifactBundleId",
"pinnedVersionId"
],
"properties": {
"cadence": {
"type": "string"
},
"repeats": {
"type": "integer",
"maximum": 5,
"minimum": 2
},
"pinnedVersionId": {
"type": "string",
"format": "uuid"
},
"artifactBundleId": {
"type": "string",
"format": "uuid"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
},
"title": "Create drift monitor"
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/com.rubrkit/rubrkit"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/com.rubrkit/rubrkit"}) over MCP.
rubrkit_run_evals ~315 tokensrubrkit_start_audit ~247 tokensrubrkit_export_proof_report ~221 tokensrubrkit_compact_artifact_file ~217 tokensrubrkit_add_golden_case ~186 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fcom.rubrkit%2Frubrkit?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fcom.rubrkit%2Frubrkit?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.rubrkit%2Frubrkit.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.rubrkit%2Frubrkit.svg :target: https://glimind.com/server/mcp-registry%2Fcom.rubrkit%2Frubrkit?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:b431ceba6344a6af…, first seen 2026-10-17, included at leaf 4512 of 69,262. Version history · verify what your client received.
Compare: most reliable knowledge servers · most reliable files servers · most reliable data servers · most reliable productivity servers · most reliable devops servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-25 23:17 UTC, the Rubrkit MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Rubrkit MCP server advertises 41 tools, including rubrkit_add_golden_case, rubrkit_apply_audit_rewrite, rubrkit_apply_deep_compaction, rubrkit_compact_artifact_file, rubrkit_create_artifact_bundle.
Point your MCP client at this streamable-http endpoint: https://www.rubrkit.com/api/v1/mcp
Glimind scanned all 41 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.