Marrow AI: Control Layer for AI Agents

Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.

What does this entry provide?

Marrow AI: Control Layer for AI Agents is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 78/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding Marrow AI: Control Layer for AI Agents to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: Official MCP Registry
Quality: 78/100
Install method: npm
Repo: getmarrow/marrow-mcp
Repo updated: Oct 26, 2026

Install command

npx -y @getmarrow/mcp@3.9.108

Install method: npm

Review the upstream source before running this command.

GitHub project Homepage

Quality

Repo stars

Repo updated

Oct 26, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-10-26T20:33:24.422509Z",
      "publishedAt": "2026-10-26T20:33:24.422509Z",
      "statusChangedAt": "2026-10-26T20:33:24.422509Z"
    }
  },
  "server": {
    "name": "ai.getmarrow/marrow",
    "icons": [
      {
        "src": "https://getmarrow.ai/brand/marrow-logo-512.png",
        "sizes": [
          "512x512"
        ],
        "mimeType": "image/png"
      },
      {
        "src": "https://getmarrow.ai/favicon.svg",
        "sizes": [
          "any"
        ],
        "mimeType": "image/svg+xml"
      }
    ],
    "title": "Marrow AI: Control Layer for AI Agents",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "version": "3.9.108",
    "packages": [
      {
        "version": "3.9.108",
        "transport": {
          "type": "stdio"
        },
        "identifier": "@getmarrow/mcp",
        "registryType": "npm",
        "environmentVariables": [
          {
            "name": "MARROW_API_KEY",
            "isSecret": true,
            "isRequired": true,
            "description": "Named Marrow agent API key. Keep it in trusted secret storage."
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/getmarrow/marrow-mcp",
      "source": "github"
    },
    "websiteUrl": "https://getmarrow.ai/marrow-for-mcp",
    "description": "Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client."
  }
}

Report an issue with this listing