M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
M

MartinLoop MCP Server

Community
An independent control layer that gives AI coding agents budgets, brakes, and receipts
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #2 of 438
Stars
★ 413 Popular
Transport
stdio (local process)
Runtime
Node.js 20+
Credentials
No credential needed
License
Apache-2.0
Last commit
79FMRS · B

MartinLoop MCP Server has a clear thesis: autonomous AI coding agents need an independent governance layer with budget caps, verifier gates, policy checks, failure classification, and signed receipts. Documentation is thorough, with reproducible demos and benchmark lanes, and it supports many hosts and adapters. Best suited to teams scaling governed agent execution; individual developers with small projects may find the ceremony heavy. Pay attention to cost-provenance labels and receipt integrity requirements.

Strongest · Documentation 18/20 Weakest · Reliability 12/20

Reliability
12/20
Security and permissions
18/20
Maintenance
16/20
Documentation
18/20
Setup experience
15/20
Why each score
Reliability 12/20
The project has a complete CI/CD pipeline and test suite, but static analysis cannot verify all key paths. The MCP server implementation follows standard patterns with clear tool definitions and error handling mechanisms. Since no actual runtime evidence is available, the reliability score is conservative.
Security and permissions 18/20
The project follows the principle of least privilege, controls execution scope through policies, and has clear boundary checks and verification mechanisms. Sensitive operations require confirmation, and credential handling is secure. No obvious security risks were found, but static analysis cannot fully verify all security boundaries.
Maintenance 16/20
The project has clear version management and release processes, timely dependency updates, and explicit license and security response channels. The project is active with continuous commits and issue responses. Dependency management is规范 with no obvious maintenance risks identified.
Documentation 18/20
Documentation is comprehensive and detailed, including installation guides, tool parameter descriptions, limitations, and troubleshooting information. It includes abundant examples and clear configuration references. Documentation aligns with code capabilities without contradictions or hidden assumptions.
Setup experience 15/20
The installation process is straightforward with clear configuration examples and host integration guides. It supports multiple platforms and mainstream clients. While static analysis cannot verify all installation scenarios, the provided configuration documentation is clear and complete.

Static review · not runListed 2026-09-07

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local filesRuns commands or codeUses the network

Best for

  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow

Not for

  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)

Required permissions

  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)

Risks and side effects

  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries

Setup

Before you start

Runtime：Node.js 20+

Run npx -y @martinloop/mcp to start the MCP server, or add it via host commands such as claude mcp add --transport stdio --scope user martin-loop -- npx -y @martinloop/mcp or codex mcp add martin-loop -- npx -y @martinloop/mcp. You can also generate config from the root CLI with npx martin-loop mcp print-config --host <codex|claude|gemini|cursor|vscode|copilot|continue|generic> or use npx martin-loop mcp install --host <host> (supports dry-run, verify-install, rollback, and uninstall). Requires Node.js 20+.

.mcp.json 
{
  "command": "npx",
  "args": [
    "-y",
    "@martinloop/mcp"
  ]
}

Shown for Claude Code. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

Generate and validate client config

Check that it works

Start the server with npx -y @martinloop/mcp and confirm MartinLoop's MCP tools appear in your client's tool list; you can also run npx -y martin-loop@latest --version first to confirm the CLI is installed.

Troubleshooting

  1. Run `martin-loop doctor` first to check the environment
  2. Use `martin-loop preflight <objective> --verify "npm test"` to validate the task and environment before executing
  3. Check integrity verdicts (verified/tamper_detected/unsigned) with `martin-loop runs verify --latest` or `dossier --latest`
  4. For MCP install issues use `mcp verify-install`, `mcp rollback`, `mcp uninstall`, or preview changes with `mcp install --dry-run`
  5. Avoid bare `npx martin-loop` (may resolve a stale local cache); use `martin-loop@latest` or pin a version

Things to try

Once connected, you can ask your AI assistant things like:

  • Run a governed coding task: summarize the demo workspace and prove tests still pass, verifying with npm test, capped at a 2 USD budget and 1 iteration.
  • Show the dossier for the latest governed run, including budget used, verifier result, and stop reason.
  • Generate a shareable receipt bundle for the latest run (run-receipt. and run-receipt.md).
  • Verify the integrity of the latest run record and tell me whether it reports verified or tamper_detected.

Use cases

Set hard budget caps and stop conditions for autonomously running AI coding agents
Require a real verification command (e.g. npm test) before work counts as complete
Produce signed run receipts and shareable audit evidence
Preserve rollback evidence so failed attempts do not silently leave unsafe changes
Integrate budget gating into CI via GitHub Actions

Supported clients

Claude Code
Codex
Gemini CLI
Cursor
VS Code
GitHub Copilot
Continue

Listed from the project's documentation, not tested by this site.

Overview

MartinLoop MCP Server is the Model Context Protocol entry point for MartinLoop, an independent control layer for autonomous AI coding agents. It gives every run an explicit contract: objective, verifier plan, budget, allowed/denied paths, and stop conditions. It enforces hard budget caps (USD/tokens/iterations), verifier gates (e.g. npm test), policy checks against unsafe commands and risky paths, a 13-class runtime failure taxonomy, HMAC-signed run records, and rollback evidence. Runs become inspectable proof receipts that can be shared. The MCP integration gives hosts one write-capable execution entrypoint plus planning, inspection, and review helpers, over stdio. The standalone MCP package is version 0.6.0, licensed Apache-2.0.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 63.3k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision eca49c35bc88 Data synced 2026-10-19 Read the FMRS scoring method