Vercel MCP in Claude Code

Quick answer: Install the Vercel MCP server with npx -y @vercel/mcp-server, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on @vercel/mcp-server as of April 15, 2026.

The Vercel MCP server gives Claude Code a tool surface on the Vercel API. After setup, the model can list projects, trigger deploys, read deployment logs, manage env vars, and inspect domains. The server is maintained by Vercel as @vercel/mcp-server and uses a personal or team access token for auth.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Vercel server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Vercel day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed include list_projects, get_project, list_deployments, get_deployment, get_build_logs, get_runtime_logs, list_env_vars, create_env_var, delete_env_var, list_domains, create_deployment. Deployment IDs are the canonical handle; URLs can change on promotion. For cron and monitoring, pair with the Vercel integrations API.

Prerequisites

A Vercel account, an access token from vercel.com/account/tokens (or a team-scoped token from the team settings), Node 20 or later. The token inherits the permissions of the user or team it was issued for.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y @vercel/mcp-server

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "vercel": {
      "command": "npx",
      "args": ["-y", "@vercel/mcp-server"],
      "env": {
        "VERCEL_TOKEN": "XXX"
      }
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• List every project in my team and tell me the production URL for each.
• Show the last 5 deployments for project website and tell me which succeeded and which failed.
• Read the build logs for the most recent failed deployment and summarize the error.
• Add an environment variable STRIPE_KEY with value sk_live_XXX to project checkout for production scope.
• Trigger a new production deploy of project marketing from the git branch main.
• List every domain attached to project landing-page and tell me which ones are verified.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

The token lives in VERCEL_TOKEN. For team access, also set VERCEL_TEAM_ID. Personal tokens have full account permissions; team tokens can be scoped to specific teams. Rotate via the same tokens page if compromised. Environment variables set through the MCP server are encrypted at rest by Vercel, but keep the token itself out of committed files.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Tool calls return 403. The token does not have access to the project you are asking about. Personal tokens only see projects owned by your user; team projects need a team-scoped token plus the correct VERCEL_TEAM_ID.

Deploy trigger returns immediately with no build. Vercel creates the deployment asynchronously. Ask Claude to poll the deployment status by ID until it reaches ready or error state, rather than expecting immediate logs.

Env var update succeeds but build still uses old value. Env vars apply to the next build, not retroactively. Trigger a fresh deploy after setting the var, or use the redeploy tool to rebuild with the new value.

Logs tool returns truncated output. Build logs cap at around 10 MB per deployment. For very long builds, ask Claude to fetch a specific time range or filter by log level rather than dumping the full log.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Vercel server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.