Log inSubmit server
Vercel MCP Pro logo

Vercel MCP Pro

Exposes 70 Vercel REST API tools for deployments, projects, domains, DNS, logs, teams, and more.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Vercel MCP Pro

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "vercel-mcp-pro": {
      "command": "npx",
      "args": [
        "-y",
        "vercel-mcp-pro"
      ],
      "env": {
        "VERCEL_TOKEN": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 70 tools correctly (6d ago).

Overview

Vercel MCP Pro MCP server exposes Vercel's REST API through 70 MCP tools for deployments, projects, environment variables, domains, DNS, aliases, certificates, logs, checks, webhooks, Edge Config, teams, and log drains. It authenticates with a Vercel access token and can optionally scope requests to a team. Use it from supported MCP clients when agents need to inspect or change Vercel resources without an OAuth flow. A readonly mode, raw endpoint tool, and optional Claude Code CLI skill cover auditing, less common API operations, and terminal-based deployments.

Use cases

  • Diagnose failed deployments with deployment events and build logs
  • Promote or roll back deployments
  • Manage project environment variables
  • Configure domains and DNS records
  • Audit Vercel resources in readonly mode

Key features

  • 70 Vercel REST API tools
  • Raw versioned endpoint access
  • Readonly safety mode
  • Team ID or slug scoping
  • Automatic retries and rate-limit handling
  • Optional Claude Code Vercel CLI skill

Tools70

What Vercel MCP Pro lets your agent do. Expand a tool for its parameters.

Verified live~11.3k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

5/5 checks healthy over the last 36d

What it can do

From the 70 tools this server returned when we ran it.

Can delete or modify data · 12Handles credentials · 1Makes network requests · 7Read-only tools · 58
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age129 days
Maintainers1

Observed 2026-10-17 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 16d ago via OSV.dev · vercel-mcp-pro (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads514Package downloads in the last 30 days.
Last commit7d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed70Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Vercel MCP Pro works

What Vercel MCP Pro MCP server does

Vercel MCP Pro MCP server connects MCP clients to the Vercel REST API through a Node.js package that can be started with npx or built locally from the repository. Its tool set covers the main operational areas of a Vercel account: deployments, projects, environment variables, domains, DNS records, aliases, certificates, build and runtime logs, checks, webhooks, Edge Config, teams, integrations, and log drains.

The server supports both read and write operations. For example, an agent can list failed deployments, retrieve build logs, promote or roll back a deployment, add environment variables, manage project domains, or update DNS records. It also exposes user and team information, along with operations for deployment files and promotion aliases.

How it works

Authentication uses a Vercel personal or team access token in the VERCEL_TOKEN environment variable. Requests can be scoped with either a team ID or team slug. The server handles authorization headers, retries for rate limits, server errors, and network failures, and applies a configurable request timeout.

The vercel_raw tool accepts an HTTP method, a versioned Vercel API path, parameters, and an optional body. This provides access to endpoints not represented by the named tools, including newer or niche REST API areas. Raw paths are restricted to Vercel's API host and must use an approved versioned path format.

Vercel MCP Pro MCP server can run in readonly mode by setting VERCEL_READONLY=true. That blocks write and delete tools and permits raw GET requests. The separate VERCEL_DISABLE_RAW=true option removes the raw endpoint tool altogether.

Setup and configuration

Create a Vercel token, then start the package with:

Terminal
npx -y vercel-mcp-pro

The repository can also be cloned, installed, and built with npm install && npm run build. Configure the MCP client to launch the package over its command and arguments, then provide the token through the client's environment settings. The README includes configurations for Claude Code, Claude Desktop, and Cursor.

VERCEL_TEAM_ID sets a default team scope by ID, while VERCEL_TEAM_SLUG provides the slug-based alternative. VERCEL_TIMEOUT_MS changes the request timeout from its 60-second default, and VERCEL_MAX_RETRIES changes the default retry count of three. The optional /vercel skill uses the official Vercel CLI for terminal commands such as deploy, logs, environment variables, and rollback.

Tools and capabilities

The 70 named tools are organized by resource type. Deployment tools list, inspect, create, cancel, delete, promote, and roll back deployments, and can retrieve deployment events, files, and file contents. Project tools manage project records and pause or resume projects. Environment-variable tools create, update, bulk-create, inspect, and remove variables.

Additional groups handle domain verification and project-domain assignments; DNS record changes; alias assignment; certificate issuance, upload, and removal; build and runtime logs; checks; webhooks; Edge Config records; team membership; integrations; and log drains. The raw tool extends coverage beyond those groups.

Limitations and notes

Readonly mode does not prevent reads of sensitive values. Tools such as list_env_vars with decryption enabled, get_env_var, and get_edge_config_items may return decrypted secrets to the model. Use the server only where that data exposure is acceptable, and disable raw access when unrestricted endpoint access is unnecessary.

The server requires a Vercel token; it does not use an OAuth flow. The bundled CLI skill is intended for Claude Code, while the MCP tools themselves are designed for MCP clients that can launch the package. ChatGPT is named as compatible in the README, but it is not one of the standardized client slugs used by this directory.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Vercel MCP Pro

Vercel MCP Pro is an MCP server that connects AI clients to the Vercel REST API using an access token. Its main tools manage deployments, projects, environment variables, domains, DNS, aliases, certificates, logs, checks, webhooks, Edge Config, teams, integrations, and log drains, with a raw endpoint tool for additional API coverage.

Install it by running `npx -y vercel-mcp-pro`, or clone the repository and build it locally with `npm install && npm run build`. Add the command to your MCP client's server configuration and provide `VERCEL_TOKEN` in its environment.

Add an `mcpServers` entry that runs `npx` with `-y vercel-mcp-pro`, then set `VERCEL_TOKEN` in the entry's environment. The README provides platform-specific Claude Desktop configuration paths for Windows and macOS.

Yes. Vercel MCP Pro works with Cursor by placing the MCP server configuration in `.cursor/mcp.json` and supplying the Vercel access token through the configuration's environment settings.

Set `VERCEL_READONLY=true` to block write and delete tools. Read operations remain available, including reads that can expose decrypted environment variables or Edge Config values, so readonly mode is not a guarantee that secrets stay hidden from the model.

Related MCP servers

All in Cloud Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewVercel MCP Pro AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/vercel-mcp-pro?style=directory)](https://allmcps.com/mcp/vercel-mcp-pro)
HTML Embed
<a href="https://allmcps.com/mcp/vercel-mcp-pro"><img src="https://allmcps.com/api/badge/vercel-mcp-pro?style=directory" alt="Vercel MCP Pro on AllMCPs" /></a>