AI Development Assistant MCP Server
by kleneway
This project provides intelligent coding assistance through custom AI tools as a Model Context Protocol (MCP) server for Cursor. It's designed as a tutorial demo to showcase the capabilities.
Last updated: N/A
What is AI Development Assistant MCP Server?
This is a Model Context Protocol (MCP) server that integrates with Cursor, providing AI-powered coding assistance through tools like code architecture planning, UI screenshot analysis, and code review functionalities.
How to use AI Development Assistant MCP Server?
First, set up your API keys in src/env/keys.ts. Then, install dependencies (npm install or yarn install) and build the server (npm run build). Add it as a new MCP server in Cursor settings, specifying the path to the built index.js file. Once added, the tools are available in Cursor's Composer.
Key features of AI Development Assistant MCP Server
Code Architect for generating coding plans
Screenshot Buddy for UI analysis
Code Review using git diffs
Integration with Cursor's Composer
Use cases of AI Development Assistant MCP Server
Generate plans for coding agents
Analyze UI design screenshots
Review code for best practices
Architect a new feature
FAQ from AI Development Assistant MCP Server
What is Cursor?
What is Cursor?
Cursor is a code editor designed for pair-programming with AI.
What is MCP?
What is MCP?
Model Context Protocol (MCP) is a standard for integrating AI tools within code editors like Cursor.
Where do I add my API Keys?
Where do I add my API Keys?
You should add your API keys in the src/env/keys.ts file. Remember this is a tutorial demo and not secure for production.
Why are tools aren't showing up in cursor?
Why are tools aren't showing up in cursor?
Try deleting you server and re-adding it. When adding your new server, make sure to select stdio. You also might need to use the full path to your project's built index.js file. Then refresh by hitting the refresh button in the top right corner.
Can I use this in production?
Can I use this in production?
You probably shouldn't, since this is a tutorial demo and not a production-ready tool. However, feel free to fork it and make it your own!