# MartinLoop MCP

> Use this tool when you need to govern AI coding agents with controlled budgets and verifiable outputs. The MartinLoop MCP provides a server-based solution for managing AI coding tasks, solving problems related to uncontrolled agent behavior and unverified results. It accepts coding tasks and budgets as inputs, and outputs inspectable runs and verified results, ideal for use cases requiring transparency and accountability in AI-driven coding processes.

Canonical page: https://skillsregistry.net/skills/io-github-keesan12-martin-loop  
JSON: https://api.skillsregistry.net/v1/skills/io-github-keesan12-martin-loop

## Description

Governed MCP server for AI coding agents with budgets, verifier gates, and inspectable runs.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.1.4
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-05-20

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.Keesan12%2Fmartin-loop)
- **Repository:** <https://github.com/Keesan12/martin-loop>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "io-github-keesan12-martin-loop"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-keesan12-martin-loop` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-keesan12-martin-loop/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt