Marrow AI: Control Layer for AI Agents runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 24 Oct 2026.
Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.
What the code does
We read the source, 22 h ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
// contexts and `rm -rf` only outside the workspace and temporary folders: that is S2 and S5.
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
'~/bin/**', '~/.local/bin/**', '/usr/local/bin/**', '/opt/homebrew/bin/**', '**/node_modules/.bin/**', '~/Library/LaunchAgents/**']);
const child = spawn(process.execPath, [process.argv[1], 'background-nudge'], {
const userConfig = resolve(home, '.npmrc');
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Marrow AI: Control Layer for AI Agents and you get told the day something new turns up.
Alternatives to Marrow AI: Control Layer for AI Agents
same job, measured the same wayLocal mandate gate and proof trail for AI agents that take consequential actions.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Marrow AI: Control Layer for AI Agents — questions
Answers built from our own checks of this server.