vercel-ai-docs-mcp

vercel-ai-docs-mcp

12
developer_toolsknowledge_and_memory

The Vercel AI SDK Documentation MCP Agent is a server that enhances the capability to query Vercel AI SDK documentation through AI-powered searches. It supports semantic search and natural language processing to provide developers with accurate responses. This project integrates with various AI systems using the Model Context Protocol.

Vercel AI SDK Documentation MCP Agent

A Model Context Protocol (MCP) server that provides AI-powered search and querying capabilities for the Vercel AI SDK documentation.

Features

  • Direct documentation search using similarity search.
  • AI-powered agent for natural language queries.
  • Session management for maintaining conversation context.
  • Automated indexing tool for the latest documentation.

Architecture

  • MCP Server: Integrates with AI assistants via Model Context Protocol.
  • DocumentFetcher: Crawls Vercel AI SDK documentation.
  • VectorStoreManager: Manages FAISS vector index.
  • AgentService: AI-powered answers using Google Gemini model.
  • DirectQueryService: Semantic documentation search.

Setup Instructions

  1. Install Node.js 18+ and npm.
  2. Clone the repository and install dependencies.
  3. Build and start the MCP server.

Integration

Integrates with Claude Desktop and other MCP clients like Cursor.