AI Dev Toolkit - MCP Server
@ReadyPlayerSix
AI Dev Toolkit - MCP Server について
A comprehensive MCP server combining file system access, AI Librarian, context compression, and project scaffolding tools
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"ai-dev-tookit": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is AI Dev Toolkit - MCP Server?
A pre‑alpha Model Context Protocol (MCP) server that combines file system tools, an AI Librarian for persistent code comprehension, project scaffolding, a structured Think Tool, and future context compression. It is designed to enhance AI assistants like Claude by giving them direct access to development workflows on the user’s local machine.
How to use AI Dev Toolkit - MCP Server?
Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, then start the server with python src/server.py. Connect Claude Desktop by either running connect_to_claude.bat (Windows, administrator) or by manually adding a server in Settings > MCP Servers with name “AI Dev Toolkit” and URL http://localhost:8000. Once connected, invoke tools in Claude by typing @AI Dev Toolkit.
Key features of AI Dev Toolkit - MCP Server
- File System Tools: read, write, edit, navigate, and search files.
- AI Librarian: persistent, auto‑updated code comprehension across sessions.
- Project Starter: generate project plans, directory structures, and starter code.
- Think Tool: a scratchpad for structured reasoning and problem solving.
- Context Compression (coming soon): store conversation history for session continuity.
Use cases of AI Dev Toolkit - MCP Server
- Maintain awareness of a codebase across multiple Claude conversations using the AI Librarian.
- Scaffold new projects with boilerplate, directory structure, and starter files.
- Reason through complex development problems step‑by‑step with the Think Tool.
- Perform everyday file operations (read, write, search, edit) entirely through Claude.
- Plan and set up GitHub repositories with automated instructions.
FAQ from AI Dev Toolkit - MCP Server
Is this server ready for production use?
No. The project is in pre‑alpha development and is not ready for production. Tools are actively being developed and may change significantly.
What are the runtime requirements?
Python 3.8 or higher, an MCP‑compatible AI assistant (e.g., Claude Desktop), and administrator privileges on Windows if using the automatic connection script.
How do I connect the server to Claude Desktop?
On Windows, run connect_to_claude.bat as administrator. Alternatively, manually add a server in Claude Desktop (Settings > MCP Servers > Add Server) with the name “AI Dev Toolkit” and the URL http://localhost:8000.
Where does the server store its data?
The AI Librarian and future Context Compression tools store data locally in files within the project directory, including the .ai_reference folder. No external databases are used.
How do I start the server?
From the repository root, run python src/server.py. Ensure all dependencies are installed and that port 8000 is not already in use.
「開発者ツール」の他のコンテンツ
MCP Unity Editor (Game Engine)
CoderGamesterModel Context Protocol (MCP) plugin to connect with Unity Editor — designed for Cursor, Claude Code, Codex, Windsurf and other IDEs
Minecraft MCP Server
yuniko-softwareA Minecraft MCP Server powered by Mineflayer API. It allows to control a Minecraft character in real-time, allowing AI assistants to build structures, explore the world, and interact with the game environment through natural language instruction
Code Index MCP
johnhuang316A Model Context Protocol (MCP) server that helps large language models index, search, and analyze code repositories with minimal setup
MCP server to deploy code to Google Cloud Run
GoogleCloudPlatformMCP server to deploy apps to Cloud Run
@vercel/mcp-adapter
vercelEasily spin up an MCP Server on Next.js, Nuxt, Svelte, and more
コメント