Getting started with Vercel

Install the Vercel CLI and deploy your app. If you use an AI coding agent, add agent support and connect Vercel MCP so it can work with your Vercel account.

• A Vercel account
• Node.js 18+

Every Vercel workflow starts with the CLI. Install it whether or not you use an AI coding agent. Agents that can run terminal commands use the CLI to deploy, pull environment variables, and manage projects.

1. Install Vercel CLI

   pnpmyarnnpmbun

   Terminal

   pnpm i -g vercel

   Terminal

   yarn global add vercel

   Terminal

   npm i -g vercel

   Terminal

   bun add -g vercel

2. Log in to Vercel

   vercel login

   Follow the prompts to authenticate with your Vercel account.

3. Deploy your project

   Navigate to your project directory and run:

   vercel

   The CLI detects your framework, builds your project, and deploys it. To deploy to production:

   vercel --prod

See the CLI documentation for the full command reference.

If you use Claude Code, OpenAI Codex, Grok Build, Cursor, GitHub Copilot, or Kimi Code, install the Vercel Plugin. It gives your agent deployment skills, framework best practices, and slash commands like /vercel-plugin:deploy prod and /vercel-plugin:env.

npx plugins add vercel/vercel-plugin

In OpenCode, install it with OpenCode's plugin command instead:

opencode plugin add github:vercel/vercel-plugin

The plugin activates automatically. No configuration needed.

See the Vercel Plugin documentation for the full list of skills, specialist agents, and slash commands.

If your agent is not in the plugin list above, install Vercel Skills instead. Skills give your agent deployment and framework guidance in a format compatible with Skills.sh.

npx skills add vercel-labs/agent-skills

To install a specific skill:

npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices

See Agent Skills for the full list.

Connect the Vercel MCP server so your agent can search the docs, manage projects and deployments, and query Web Analytics.

npx -y add-mcp https://mcp.vercel.com -g

See Vercel MCP for client-specific setup.

If your project needs a database, blob storage, or another backing service, you can provision one from the CLI and have Vercel wire the credentials into your project automatically.

Run vercel install (alias for vercel integration add) to install a Marketplace integration, provision a resource, connect it to the currently linked project, and sync environment variables into .env.local:

vercel install neon
vercel install upstash
vercel install supabase

Add --help to any command to see integration-specific products, metadata options, and billing plans. For non-interactive flows, pass options as flags:

vercel install neon --name my-database --plan free -e production -e preview

See Storage on Vercel Marketplace for the full list of storage integrations.

You can also deploy without the CLI. Go to the New Project page, connect your GitHub, GitLab, or Bitbucket account, select a repo, and click Deploy. Every push to your connected branch triggers a new deployment automatically.

• Fundamental concepts – How requests, builds, and compute work on Vercel
• Explore Vercel products – Browse the full catalog of Vercel products and capabilities
• Set up environment variables
• Add a custom domain
• Explore supported frameworks
• Vercel Functions – Run server-side code on demand
• Storage on Vercel Marketplace – Provision Postgres, Redis, NoSQL, and more with vercel install
• Agent resources – Documentation access, skills, and CLI workflows for AI agents