AI Dev Toolkit MCP Server

@ReadyPlayerSix

Basic information

About AI Dev Toolkit MCP Server

The AI Dev Toolkit is an all-in-one solution for managing Model Context Protocol (MCP) servers and enhancing AI assistants like Claude with advanced development capabilities.

AI Dev Toolkit MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ai-dev-toolkit": {
      "command": "python",
      "args": [
        "install_unified.py"
      ]
    }
  }
}

AI Dev Toolkit MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is AI Dev Toolkit?

AI Dev Toolkit is an MCP server that enhances Claude Desktop with persistent code context, filesystem access, development tools, and AI-powered task management. It bridges projects and Claude, enabling codebase understanding, development assistance, and context retention across conversations.

How to use AI Dev Toolkit?

Clone the repository, install dependencies with pip install -r requirements.txt, then run python install_unified.py to register the server with Claude Desktop. Use commands like initialize_librarian, find_implementation, add_todo, and think to interact with its tools.

Key features of AI Dev Toolkit

AI Librarian for persistent code understanding and search
Unified MCP Server combining librarian and file system tools
Secure file access with directory management and operations
Enhanced code analysis for references, metrics, and related files
Task management with tracking, subtasks, and AI extraction
TaskBoard System and Think Tool (beta) for asynchronous processing

Use cases of AI Dev Toolkit

Help Claude understand a new codebase before starting development
Search for functions, classes, or references across a project
Manage and track development tasks directly from conversations
Automatically extract tasks from discussions with Claude
Analyse file structure and metrics for code reviews

Frequently asked questions

What does the AI Librarian do?

It maintains a comprehensive index of your codebase, remembers code structure across conversations, tracks components like functions and classes, and provides smart search for implementations and references.

What are the prerequisites for installation?

Python 3.8 or higher and the latest version of Claude Desktop are required.

How do I configure the server?

The installation script automatically edits the Claude Desktop configuration file. Its location varies: `%APPDATA%\Claude Desktop\claude_desktop_config.json` on Windows, `~/Library/Application Support/Claude Desktop/claude_desktop_config.json` on macOS.

What should I do if the toolkit doesn't appear in Claude?

Ensure the configuration was saved correctly and restart Claude Desktop. For permission errors, check the allowed directories in the configuration. For connection issues, verify the configuration and restart the server.

What transports and authentication does the server use?

The README mentions "MCP Protocol support" and "Full compliance with Model Context Protocol standards", but does not specify transport details or authentication methods.

Comments

More Developer Tools MCP servers

Capgo MCP

Cap-go

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Nizh

Compliance frameworks delivered to AI agents. Nizh gives your agent read access to your organization's compliance program — SOC 2, ISO 27001, CMMC 2.0, NIST, and more — as MCP tools, so it can check posture, read a contr

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.