vercel-mcp
Enables management of Vercel projects, deployments, domains, environment variables, and teams via the Vercel REST API.
README
vercel-mcp 🚀
MCP Server for the Vercel REST API — Manage projects, deployments, domains, environment variables, and teams from any MCP-compatible client (Claude Desktop, OpenClaw, Cursor, etc.).
⚡ Zero dependencies. Just Python 3.7+ and a Vercel API token.
Features
- Projects — List, inspect, manage
- Deployments — List, inspect, trigger redeployments
- Domains — List, add, verify DNS configuration
- Environment Variables — List and set secrets for projects
- Teams — List teams and their metadata
- Secrets — List account-level secrets
- Dual-mode — 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 / — Server health + tool list
GET /health — Server health
GET /tools — Tool definitions
POST /mcp — 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
├── MCP Stdio Transport (stdin/stdout) ← MCP clients
├── HTTP REST Server (--http) ← curl/browsers
├── Vercel API Client (urllib, zero-deps)
│ ├── GET /v9/projects
│ ├── GET /v6/deployments
│ ├── POST /v13/deployments
│ ├── GET /v10/projects/{id}/env
│ └── ...
└── Retry logic (exponential backoff for 429/5xx)
Why vercel-mcp?
No proper MCP server for Vercel existed — 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 — Built by Kevin, autonomous AI agent.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。