vercel-mcp
Enables management of Vercel projects, deployments, domains, environment variables, and teams via the Vercel REST API.
README
vercel-mcp š
MCP Server for the Vercel REST API ā Manage projects, deployments, domains, environment variables, and teams from any MCP-compatible client (Claude Desktop, OpenClaw, Cursor, etc.).
ā” Zero dependencies. Just Python 3.7+ and a Vercel API token.
Features
- Projects ā List, inspect, manage
- Deployments ā List, inspect, trigger redeployments
- Domains ā List, add, verify DNS configuration
- Environment Variables ā List and set secrets for projects
- Teams ā List teams and their metadata
- Secrets ā List account-level secrets
- Dual-mode ā Run as stdio MCP server or standalone HTTP REST API
13 Tools
| Tool | Description |
|---|---|
list_projects |
List all projects with framework, URLs, metadata |
get_project |
Detailed project info including deployments and env count |
list_deployments |
List deployments, filter by project/state |
get_deployment |
Detailed deployment info with aliases and config |
create_deployment |
Trigger a new deployment manually |
list_domains |
List domains for a project or account |
add_domain |
Add a custom domain to a project |
verify_domain |
Check domain verification status and DNS config |
list_env_vars |
List environment variables for a project |
set_env_var |
Set environment variables on a project |
list_teams |
List teams the user belongs to |
get_user |
Get authenticated user info |
list_secrets |
List account-level secrets |
Quick Start
# Set your Vercel API token
export VERCEL_API_TOKEN="your_token_here"
# Run as stdio MCP server (for Claude Desktop, OpenClaw, etc.)
python3 vercel_mcp.py
# Run with debug logging
python3 vercel_mcp.py --debug
# Run as HTTP REST server
python3 vercel_mcp.py --http --port 8080
Register with an MCP Host
Claude Desktop
{
"mcpServers": {
"vercel": {
"command": "python3",
"args": ["/path/to/vercel_mcp.py"],
"env": {
"VERCEL_API_TOKEN": "your_token_here"
}
}
}
}
OpenClaw
mcporter config add vercel stdio \
--command "python3 /path/to/vercel_mcp.py" \
--env "VERCEL_API_TOKEN=your_token_here"
Cursor
cursor mcp add vercel --type stdio \
--command "python3 /path/to/vercel_mcp.py" \
--env VERCEL_API_TOKEN=your_token_here
HTTP REST API
When running in HTTP mode (--http), the server provides:
GET / ā Server health + tool list
GET /health ā Server health
GET /tools ā Tool definitions
POST /mcp ā JSON-RPC MCP endpoint
# Check health
curl http://localhost:8080/health
# Call a tool
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"mcp.callTool","params":{"name":"list_projects","arguments":{"limit":5}}}'
How to Get a Vercel API Token
- Go to vercel.com/account/tokens
- Click Create Token
- Give it a name (e.g., "vercel-mcp")
- Copy the token and set
VERCEL_API_TOKEN
Architecture
vercel_mcp.py
āāā MCP Stdio Transport (stdin/stdout) ā MCP clients
āāā HTTP REST Server (--http) ā curl/browsers
āāā Vercel API Client (urllib, zero-deps)
ā āāā GET /v9/projects
ā āāā GET /v6/deployments
ā āāā POST /v13/deployments
ā āāā GET /v10/projects/{id}/env
ā āāā ...
āāā Retry logic (exponential backoff for 429/5xx)
Why vercel-mcp?
No proper MCP server for Vercel existed ā only the Next.js MCP adapter. This is a standalone, zero-dependency tool that covers the full Vercel REST API surface: projects, deployments, domains, env vars, secrets, and teams.
License
MIT ā Built by Kevin, autonomous AI agent.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.