Vercel AI Docs
A Model Context Protocol (MCP) server that provides AI-powered search and querying capabilities for the Vercel AI SDK documentation. This project enables developers to ask questions about the Vercel AI SDK and receive accurate, contextualized respons
What is Vercel AI Docs?
Vercel AI Docs is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that provides ai-powered search and querying capabilities for the vercel ai sdk documentation. this project enables developers to ask questions about the vercel ai ...
A Model Context Protocol (MCP) server that provides AI-powered search and querying capabilities for the Vercel AI SDK documentation. This project enables developers to ask questions about the Vercel AI SDK and receive accurate, contextualized respons
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server that provides AI-power
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx vercel-ai-docsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Vercel AI Docs
The Vercel AI Docs MCP Server gives AI assistants semantic search access to the complete Vercel AI SDK documentation, enabling developers to ask natural language questions about the SDK and get accurate, source-grounded answers without leaving their coding environment. It exposes two query tools — an AI agent mode that synthesizes answers from multiple documents and a direct vector-similarity mode for fast lookup — plus session memory so follow-up questions stay in context. This is particularly useful when you are building streaming, tool-calling, or multi-modal applications with the Vercel AI SDK and need to look up API signatures or usage patterns mid-conversation.
Prerequisites
- Node.js 18 or higher installed
- npm installed
- A Google AI Studio API key for Gemini (free at https://makersuite.google.com/app/apikey)
- An MCP-compatible client such as Claude Desktop or Cursor
Clone the repository
Download the server source code. This server is not published to npm and must be built locally.
git clone https://github.com/IvanAmador/vercel-ai-docs-mcp.git
cd vercel-ai-docs-mcpInstall dependencies
Install all Node.js packages required by the server.
npm installCreate your .env file with a Google AI key
The server uses Gemini to power its AI agent query tool. Set your Google AI Studio key in a .env file.
echo 'GOOGLE_GENERATIVE_AI_API_KEY=your-google-api-key-here' > .envBuild the TypeScript source and generate the documentation index
Compile the TypeScript and run the indexer to create the local vector index of Vercel AI SDK docs.
npm run build
npm run build:indexStart the server and configure Claude Desktop
Add the server to claude_desktop_config.json using 'node' to run the compiled output directly.
{
"mcpServers": {
"vercel-ai-docs": {
"command": "node",
"args": ["/path/to/vercel-ai-docs-mcp/dist/index.js"],
"env": {
"GOOGLE_GENERATIVE_AI_API_KEY": "your-google-api-key-here"
}
}
}
}Vercel AI Docs Examples
Client configuration
Add this to claude_desktop_config.json. Update the path to match where you cloned the repository and compiled the TypeScript.
{
"mcpServers": {
"vercel-ai-docs": {
"command": "node",
"args": ["/Users/you/vercel-ai-docs-mcp/dist/index.js"],
"env": {
"GOOGLE_GENERATIVE_AI_API_KEY": "your-google-api-key-here"
}
}
}
}Prompts to try
Ask about Vercel AI SDK features using the agent-query tool for synthesized answers or direct-query for fast similarity search.
- "How do I use the streamText function to stream a response from OpenAI?"
- "What is the difference between useChat and useCompletion hooks?"
- "Show me how to implement tool calling with the Vercel AI SDK"
- "How do I set up a multi-step agent with maxSteps in the AI SDK?"
- "What providers are supported by the AI SDK and how do I switch between them?"Troubleshooting Vercel AI Docs
GOOGLE_GENERATIVE_AI_API_KEY is invalid or missing error on startup
Ensure you created a .env file in the project root with your key, or that the key is passed in the 'env' block of claude_desktop_config.json. Get a free key at https://makersuite.google.com/app/apikey.
agent-query returns no results or generic answers
Run 'npm run build:index' to regenerate the documentation vector index. If the index build step was skipped, the server has no docs to search against.
Server crashes with 'Cannot find module' after npm install
Run 'npm run build' before starting the server — the TypeScript must be compiled to the dist/ directory first. The server entrypoint is dist/index.js, not src/index.ts.
Frequently Asked Questions about Vercel AI Docs
What is Vercel AI Docs?
Vercel AI Docs is a Model Context Protocol (MCP) server that model context protocol (mcp) server that provides ai-powered search and querying capabilities for the vercel ai sdk documentation. this project enables developers to ask questions about the vercel ai sdk and receive accurate, contextualized respons It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Vercel AI Docs?
Follow the installation instructions on the Vercel AI Docs GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Vercel AI Docs?
Vercel AI Docs works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Vercel AI Docs free to use?
Yes, Vercel AI Docs is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Vercel AI Docs Alternatives — Similar Developer Tools Servers
Looking for alternatives to Vercel AI Docs? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Vercel AI Docs in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Vercel AI Docs?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.