martin-loop

A local server for AI coding agents that provides checks before and after work, limits on execution, and verified handoffs. MCP is a standard way for an AI agent to call external tools.

In plain words
What is it for?
Use it to run verifier gates, enforce stop limits, control an agent's execution, and produce a handoff containing evidence of the result.
Why use it?
It adds recorded boundaries and verification around coding-agent work, so completion is based on checks rather than only the agent's claim.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/keesan12/martin-loop/martinloop-martin-loop
Clone the repo
git clone --depth 1 https://github.com/Keesan12/martin-loop

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

martin-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/martinloop/.mcp.json · 9 lines

What it actually says

{
  "martin-loop": {
    "command": "npx",
    "args": [
      "-y",
      "@martinloop/[email protected]"
    ]
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 9 lines scan A 6888882e891c

Subscribe to this mod's changes

martin-loop is an MCP server published in the GitHub repository Keesan12/martin-loop (47 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other mcp servers, from other repositories

aegis

Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes. Runs locally from the agent-aegis Python package. Needs 1 environment variable to run.

Acacian/aegis · not measured

mila-sek

MCP server "mila-sek" as configured in dingdawg/dingdawg-agent-1. Runs mila_os.mcp_server with /home/joe-rangel/Desktop/Jarvis-Main-Brain/mila_os/mcp_server/.venv/bin/python3. Needs 1 environment variable to run.

dingdawg/dingdawg-agent-1 · not measured

dingdawg-code-review

AI code review — security, quality, performance. Learns your patterns. Receipted. Runs locally from the dingdawg-code-review npm package. Needs 1 environment variable to run.

dingdawg/dingdawg-agent-1 · not measured

dingdawg-data-agent

AI data agent — schema analysis, query optimization, PII detection, pipelines. Runs locally from the dingdawg-data-agent npm package. Needs 1 environment variable to run.

dingdawg/dingdawg-agent-1 · not measured

dingdawg-devops-agent

DevOps AI. Deploy checks, incident analysis, infra audit. Learns from past failures. Runs locally from the dingdawg-devops-agent npm package. Needs 1 environment variable to run.

dingdawg/dingdawg-agent-1 · not measured

dingdawg-legal-agent

AI contract review, clause drafting, compliance checklists & legal research. Runs locally from the dingdawg-legal-agent npm package. Needs 1 environment variable to run.

dingdawg/dingdawg-agent-1 · not measured