Skip to main content
MCP server CX Codex

Martin Loop — Claude Code MCP server: what it does, install

Martin Loop puts budgets, stop conditions, verification, and recovery around coding-agent jobs. Use it when a run needs a clear handoff and stored evidence.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add martin-loop -- npx -y @martinloop/mcp
Open on GitHub

What Martin Loop does

Martin Loop manages the work around a coding agent. You define an objective, success check, budget, edit scope, and iteration cap; the system then moves through preflight, control, verification, recovery, proof, and analysis. The agent still writes the code. Martin Loop keeps the run bounded and records its outcome.

Configured verifier commands provide fresh evidence tied to the active run and workspace. Inspect the latest result with martin dossier --latest, then validate stored integrity with martin runs verify --latest. The result can be VERIFIED, STOPPED, or NEEDS REVIEW. Martin Loop does not replace Git, CI, code review, security scanners, or the coding agent.

The project requires Node >=20. Optional hosted dashboard sync uses MARTIN_API_TOKEN and MARTIN_TELEMETRY_ENDPOINT; governed work remains local-first.

What it helps with

  • define an objective, verifier, budget, and iteration cap
  • limit the agent’s edit scope and spend
  • stop retries when run conditions are reached
  • check a result with independent verifier commands
  • preserve recovery evidence for a later handoff

Example prompts for the agent

  • Run this coding task with a fixed budget, edit scope, and iteration cap.
  • Use the configured verifier commands and prepare the final handoff status.
  • Show the latest dossier and verify the integrity of the stored run.

How to install Martin Loop

Platform CLI

claude mcp add martin-loop -- npx -y @martinloop/mcp

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 Martin Loop

How do I install Martin Loop in Claude Code?

Run claude mcp add martin-loop -- npx -y @martinloop/mcp.

What does Martin Loop do?

It governs a coding-agent job from definition and preflight through control, verification, recovery, proof, and analysis. The run ends with a recorded VERIFIED, STOPPED, or NEEDS REVIEW outcome.

What does Martin Loop require to run?

The project requires Node >=20. Optional hosted dashboard sync uses MARTIN_API_TOKEN and MARTIN_TELEMETRY_ENDPOINT.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor