Skip to content
Stork.AIstork.ai

codeloop

CLI tool for CodeLoop — automated verification for AI coding agents

build.protocol_tooling.mcp#codeloop#mcp#mcp-server#cursor#cursor-ide#claude-code#testing#verification#ai-coding#ai-agent
Visit Homepage
Back to MCP Servers

Install codeloop in your MCP client

codeloop is a Model Context Protocol server. Add it to your MCP client config once, restart, and the server's tools become available to your AI assistant. The same JSON snippet below works across all four major clients — only the config file path differs.

  1. Locate your client's MCP config file.
    • Cursor: ~/.cursor/mcp.json
    • Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
    • Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json
    • VS Code: Settings → Extensions → MCP
    • Windsurf: Settings → MCP Servers
  2. Add codeloop to the mcpServers map — paste the snippet below into your config file. If you already have other MCP servers, merge the entry into the existing mcpServers object.
  3. Restart your client so it picks up the new server.
  4. Verify — ask the assistant to list available tools; codeloop's tools should appear.
{
  "mcpServers": {
    "codeloop": {
      "command": "npx",
      "args": [
        "-y",
        "codeloop"
      ]
    }
  }
}

Install codeloop in Cursor

Open ~/.cursor/mcp.json in your editor, paste the snippet above into mcpServers, save, and restart Cursor. codeloop will show up in the assistant's tool list on next launch.

Install codeloop in Claude Desktop (macOS)

Open ~/Library/Application Support/Claude/claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (macOS). codeloop will show up in the assistant's tool list on next launch.

Install codeloop in Claude Desktop (Windows)

Open %APPDATA%\Claude\claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (Windows). codeloop will show up in the assistant's tool list on next launch.

Install codeloop in VS Code

Open Settings → Extensions → MCP in your editor, paste the snippet above into mcpServers, save, and restart VS Code. codeloop will show up in the assistant's tool list on next launch.

npm package: codeloop

Transport

codeloop supports the following MCP transports. Most AI clients use stdio by default for locally-installed servers.

stdio

From the codeloop README

# `codeloop` — CLI [![npm](https://img.shields.io/npm/v/codeloop.svg)](https://www.npmjs.com/package/codeloop) [![docs](https://img.shields.io/badge/docs-codeloop.tech-blue)](https://codeloop.tech/docs) [![license](https://img.shields.io/npm/l/codeloop.svg)](./LICENSE) The command-line entry point for **CodeLoop** — the zero-LLM-cost verification layer for AI coding agents (Cursor, Claude Code, Codex, Gemini, Aider, …). The CLI is what bootstraps a project, registers the MCP server with your editor, runs the verify→diagnose→gate-check loop from a terminal, and ships diagnostics with `codeloop doctor`. CodeLoop runs **locally** as an MCP server, never spawns its own LLM calls, and works on macOS, Linux, and Windows. ## Install ```bash npx codeloop install # install M…

More build.protocol_tooling.mcp MCP servers

Other Model Context Protocol servers in the same space as codeloop. Each one adds different capabilities to your AI assistant — pick based on the data sources or workflows you need.

Browse the full MCP server directory or use Stork's one-line install to let your agent pick the right server automatically.