Vercel MCP is Vercel's official Model Context Protocol server. It is a remote server with OAuth that connects AI assistants and coding agents to your Vercel account, so they can work with your projects directly.
According to the page, it lets AI tools search and navigate Vercel documentation, manage projects and deployments, analyse deployment logs, and query visitors, page views and custom events from Web Analytics. Access depends on the server configuration, your client's OAuth grant and your team permissions.
Setup uses the server address https://mcp.vercel.com. The page offers a one-line add-mcp command that configures several AI clients at once, and gives separate instructions for Claude, ChatGPT, Codex CLI, Cursor, VS Code with Copilot, Devin, Raycast, Goose, Windsurf, Gemini Code Assist and Gemini CLI, OpenCode, Pi and fx. After you add the server, you authorise it with your Vercel account in the browser or the client.
The page is written for developers and teams who already deploy on Vercel and use AI tools for coding or operations. It also describes a client identification method for people building their own MCP clients.
Vercel MCP is available on all plans, and use is subject to Vercel's AI Product Terms. The page does not give a separate price for the server. Costs follow Vercel's usage-based pricing for the platform, with a Hobby tier that includes some usage and a Pro tier that gives a monthly credit and then charges on demand.
