Which integrations are available for this server?

Automates local Git repository management by creating feature branches and committing code changes throughout the development process. Handles the final stages of the development workflow by pushing feature branches and automatically opening pull requests on GitHub.

How do I use dev-loop-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@dev-loop-mcp Add email validation to the signup form" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

dev-loop-mcp

An MCP (Model Context Protocol) server that runs an AI-driven TDD development loop. It generalizes the dev-loop state machine to work with any project via a simple config file.

What it does

The dev-loop drives your project through these phases automatically:

INIT → DECOMPOSE → TDD_LOOP → BUILD → DEPLOY → INTEG_TEST → INTEG_FIX → QUALITY_REVIEW → CLEAN_TREE_CHECK → PUSH_AND_PR → DONE

INIT: Creates a git branch
DECOMPOSE: AI breaks your description into testable tasks
TDD_LOOP: AI writes scenarios, failing tests, then implementation (per task)
BUILD: Runs your build command
DEPLOY: Runs your deploy command (skipped if not configured)
INTEG_TEST: Runs your integration tests (skipped if not configured)
INTEG_FIX: AI fixes integration test failures (up to 5 attempts)
QUALITY_REVIEW: AI reviews and cleans up the diff
CLEAN_TREE_CHECK: Commits any stray files
PUSH_AND_PR: Pushes branch and opens a GitHub PR

Installation

npm install -g dev-loop-mcp

Or use via npx:

npx dev-loop-mcp

Configuration

Create dev-loop.config.json in your project root:

{
  "buildCommand": "npm run build",
  "testCommand": "npm test",
  "deployCommand": "npm run deploy",
  "integTestCommand": "npm run test:integ",
  "branchPrefix": "claude/",
  "model": "claude-sonnet-4-6"
}

All fields are optional. Defaults:

buildCommand: "npm run build"
testCommand: "npm test"
deployCommand: absent (DEPLOY phase skipped)
integTestCommand: absent (INTEG_TEST phase skipped)
branchPrefix: "claude/"
model: "claude-sonnet-4-6"

Environment variables

Variable	Required	Description
`ANTHROPIC_API_KEY`	Yes	Your Anthropic API key
`DEV_LOOP_ROOT`	No	Project root directory (defaults to `cwd`)

MCP setup

Add to your MCP client configuration (e.g., Claude Desktop claude_desktop_config.json):

{
  "mcpServers": {
    "dev-loop": {
      "command": "dev-loop-mcp",
      "env": {
        "ANTHROPIC_API_KEY": "sk-ant-...",
        "DEV_LOOP_ROOT": "/path/to/your/project"
      }
    }
  }
}

Available tools

`start_loop`

Start a new development loop.

{
  "description": "Add email validation to the user registration flow",
  "branch": "claude/email-validation"
}

Or with pre-decomposed tasks:

{
  "tasks": [
    {
      "id": 1,
      "title": "Add email validator function",
      "scope": "src/utils/email.ts",
      "acceptance": "validateEmail returns true for valid emails and false for invalid ones"
    }
  ],
  "branch": "claude/email-validation"
}

`resume_loop`

Resume an interrupted loop:

{}

`loop_status`

Check the current loop status:

{}

Using as a library

import { runLoop, loadConfig, RealShellAdapter, AnthropicDevWorker } from "dev-loop-mcp";
import Anthropic from "@anthropic-ai/sdk";

const config = await loadConfig("/path/to/project");
const client = new Anthropic();
const shell = new RealShellAdapter();
const aiWorker = new AnthropicDevWorker(client, config.model, shell);

const finalState = await runLoop(initialState, {
  shell,
  aiWorker,
  stateFilePath: "/path/to/project/.loop-state.json",
  repoRoot: "/path/to/project",
  config,
});

This server cannot be installed

-

security - not tested

F

license - not found

-

quality - not tested

How are these scores calculated?