Vercel MCP Integration
@nganiet
MCP server connecting Claude to Vercel
Overview
What is Vercel MCP Integration?
An MCP server that wraps Vercel's REST API into tools for AI Assistants like Claude and Cursor. It allows developers to manage deployments, projects, environment variables, and teams programmatically.
How to use Vercel MCP Integration?
Install Node.js 18+, clone the repo, run npm install, configure a .env file with your VERCEL_API_TOKEN, and start the server with npm start. Then connect your MCP client (Claude, Cursor, or custom) via stdio or HTTP. Alternatively, deploy with Docker.
Key features of Vercel MCP Integration
- List, get, and create deployments with filtering
- Create, list, and find projects
- Manage environment variables and custom environments
- List and create teams
- Supports stdio and HTTP transports
Use cases of Vercel MCP Integration
- Monitor and manage deployments via natural language
- Automate project creation and CI/CD pipelines
- Retrieve and update environment variables across projects
- Manage team membership and organization
FAQ from Vercel MCP Integration
What runtime and dependencies are required?
Node.js 18+ and a Vercel API token. The server runs locally or in Docker.
How does authentication work?
The server reads a VERCEL_API_TOKEN environment variable to authenticate with Vercel's REST API.
Can I use this with Cursor or Claude?
Yes. The README provides specific integration steps for both Claude Code and Cursor.
Does the server support HTTP transport?
Yes. You can use mcp-proxy to expose it as an HTTP server on port 3399 for clients that support HTTP.
Where does my data live?
Data stays within your Vercel account; the server acts as a proxy and does not store any data locally.
