Home / MCP servers / Marrow AI: Control Layer for AI Agents
Marrow AI: Control Layer for AI Agents
getmarrow/marrow-mcpMCP server
Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.
Why this score
Installs in real projects: we can't search for this one (it has no fixed package name or address), so it's scored as a typical MCP server.
Popularity score: 51/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Nov 4, 2026 at the npm package @getmarrow/mcp@3.9.110, with Cisco's open-source skill-scanner.
What its code does:
- Runs shell commands Common for dev tools. Read the commands it runs.scripts/control-path-canary.cjs:2
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneMarrow AI: Control Layer for AI Agents getmarrow/marrow-mcp · MCP server | 51 | ★ 7 | not measured | today |
| mac-control-mcp AdelElo13/mac-control-mcp · MCP server Both about control | 60 | ★ 18 | not measured | 20d ago |
| security-layer-auditor yonatangross/orchestkit · Subagent Both about layer | 58 | ★ 296 | ≈43 in chat | 16d ago |
| cross-layer-sync ZeroDeng01/sublinkPro · Skill Both about layer | 72 | ★ 1.7k | ≈50 always | 16d ago |
| ripwire-layers redhat-et/ripwire · Skill Both about layer | 72 | ★ 2.5k | ≈27 always | 16d ago |
| design-control-loop humanlayer/skills · Skill Both about control | 76 | ★ 5.4k | ≈59 always | 27d ago |