Marrow AI — Claude Code MCP server: features and setup
Marrow AI checks agent actions against policy and records evidence of outcomes. Use it when agents take consequential actions across a shared workflow.
claude mcp add marrow -e MARROW_API_KEY=<MARROW_API_KEY> -- npx -y @getmarrow/mcpWhat Marrow AI: Control Layer for AI Agents does
Marrow AI adds a policy check before an agent acts and records the result afterward. Its MCP tools cover status, action governance, evidence-backed task closure, and lessons shared across an agent fleet. It sits alongside existing models and agent hosts rather than replacing them.
Set MARROW_API_KEY to an API key before starting the server. In Claude Code, add it with claude mcp add, then restart the host and review hook trust. Native Windows is not supported; use WSL.
Hooks run inside the agent host, so they do not stop actions taken outside it or after someone edits the host settings. If Marrow cannot be reached, hooks hold high-risk actions while routine ones continue with a warning.
What it helps with
- check an agent action before it runs
- record evidence for a completed task
- apply prior team lessons to a later action
- enforce policy across agents and environments
Example prompts for the agent
- Check whether this release can be published and explain the decision.
- Record the task outcome with evidence that it was completed.
- Check Marrow status before changing production data.
How to install Marrow AI: Control Layer for AI Agents
Platform CLI
claude mcp add marrow -e MARROW_API_KEY=<MARROW_API_KEY> -- npx -y @getmarrow/mcpReplace <…> with your own values
Platform CLI
codex mcp add marrow-ai-control-layer-for-ai-agents --env MARROW_API_KEY=<MARROW_API_KEY> -- npx -y @getmarrow/mcpReplace <…> with your own values
Config file
{
"mcpServers": {
"marrow-ai-control-layer-for-ai-agents": {
"command": "npx",
"args": [
"-y",
"@getmarrow/mcp"
],
"env": {
"MARROW_API_KEY": "<MARROW_API_KEY>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"marrow-ai-control-layer-for-ai-agents": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@getmarrow/mcp"
],
"env": {
"MARROW_API_KEY": "<MARROW_API_KEY>"
}
}
}
}Replace <…> with your own values
Platform CLI
gemini mcp add -e MARROW_API_KEY=<MARROW_API_KEY> marrow-ai-control-layer-for-ai-agents npx -y @getmarrow/mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Marrow AI: Control Layer for AI Agents
How do I install Marrow AI in Claude Code?
Run claude mcp add marrow -e MARROW_API_KEY=<MARROW_API_KEY> -- npx -y @getmarrow/mcp. Restart Claude Code and review hook trust.
What does Marrow AI do?
It checks agent actions against policy before they happen, then records evidence and outcomes. It also makes fleet lessons available for later actions.
What does Marrow AI need to run?
Provide an API key through MARROW_API_KEY. For Windows, use WSL because native Windows is not supported.
