🤖 AI Development Assistant MCP Server
@kleneway
关于 🤖 AI Development Assistant MCP Server
Example of an MCP server with custom tools that can be called directly from cursor
基本信息
配置
工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is 🤖 AI Development Assistant MCP Server?
An AI-powered development toolkit implemented as a Model Context Protocol (MCP) server for Cursor. It provides intelligent coding assistance through custom AI tools, but is primarily a tutorial demo and not a production-ready tool.
How to use 🤖 AI Development Assistant MCP Server?
Install dependencies with npm install or yarn install, build the server with npm run build, then add it to Cursor Settings > Features > MCP as a new stdio server with the command node /path/to/dist/index.js. Once added, tools appear in Composer and can be triggered by asking the AI explicitly (e.g., “Review this code for best practices”).
Key features of 🤖 AI Development Assistant MCP Server
- Code Architect – generates plans and instructions using advanced reasoning LLMs
- Screenshot Buddy – takes UI design screenshots and uses them with the composer agent
- Code Review – uses git diffs to trigger code reviews
- Simple environment setup with API keys in
src/env/keys.ts - Integrates directly into Cursor’s composer interface
Use cases of 🤖 AI Development Assistant MCP Server
- Architecture planning for new features by generating structured code plans
- Visual UI analysis by capturing design screenshots for agent review
- Automated code review triggered by git diffs to check best practices
FAQ from 🤖 AI Development Assistant MCP Server
What dependencies are required?
Node.js and npm (or yarn) are required. An OpenAI API key must be provided in the src/env/keys.ts file or inline in the Cursor MCP interface.
Where are my API keys and data stored?
API keys are stored locally in the keys.ts file (or set inline) and sent to OpenAI when tools are used. The server runs locally and does not store user data externally.
Is this production-ready?
No. The project is explicitly described as a tutorial demo, not a production-ready tool. The author notes they likely won’t fix issues, but encourages forking.
What transport does this MCP server use?
It uses the stdio transport type, configured in Cursor as a command that runs the built dist/index.js file.
How do I trigger the tools?
The AI agent in Cursor’s Composer automatically suggests using relevant tools, or you can explicitly request them by name or description (e.g., “Analyze this UI screenshot”). The agent asks for approval before making tool calls.
开发工具 分类下的更多 MCP 服务器
Hello World MCP Server (Reference Extension)
anthropicsDesktop Extensions: One-click local MCP server installation in desktop apps
FastAPI-MCP
tadata-orgExpose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
MCP-Scan: An MCP Security Scanner
invariantlabs-aiSecurity scanner for AI agents, MCP servers and agent skills.
JetBrains MCP Proxy Server
JetBrainsA model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
test
prysmaticlabsGo implementation of Ethereum proof of stake
评论