如何将 Vercel 远程 MCP 连接到 OpenAI Codex CLI
约 1 分钟即可把 Vercel 的远程 MCP 服务端接入 OpenAI Codex CLI。如需排查 OAuth / 401 问题,可先用 OAuth 2.1 调试器体检端点。
Streamable HTTPhttps://mcp.vercel.com
Install in Cursor →
Or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"vercel": {
"url": "https://mcp.vercel.com"
}
}
}claude mcp add --transport http vercel https://mcp.vercel.com
Install in VS Code →
Or add to .vscode/mcp.json:
{
"servers": {
"vercel": {
"type": "http",
"url": "https://mcp.vercel.com"
}
}
}- Open Settings → Connectors (Integrations) → Add Custom Connector.
- Paste the endpoint URL:
https://mcp.vercel.com - Complete the browser OAuth 2.1 login flow when prompted.
Bridge the remote endpoint into stdio with mcp-remote in claude_desktop_config.json:
{
"mcpServers": {
"vercel": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.vercel.com"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"vercel": {
"serverUrl": "https://mcp.vercel.com"
}
}
}Add to ~/.kiro/settings/mcp.json (or .kiro/settings/mcp.json in your workspace), then reopen Kiro's Agent panel to pick up the server:
{
"mcpServers": {
"vercel": {
"url": "https://mcp.vercel.com"
}
}
}Add to ~/.codex/config.toml — Codex reads remote HTTP servers from [mcp_servers.*] tables:
[mcp_servers.vercel] url = "https://mcp.vercel.com"
Add to cline_mcp_settings.json (Cline → MCP Servers → Configure), or paste it via Cline's MCP marketplace file:
{
"mcpServers": {
"vercel": {
"type": "streamableHttp",
"url": "https://mcp.vercel.com"
}
}
}Add to ~/.gemini/settings.json under mcpServers — httpUrl for Streamable HTTP, url for legacy SSE:
{
"mcpServers": {
"vercel": {
"httpUrl": "https://mcp.vercel.com"
}
}
}接入步骤
- 编辑 TOML 配置 — 打开
~/.codex/config.toml,加入[mcp_servers.vercel]与url = "https://mcp.vercel.com"。 - 配置凭据 — 首次调用时客户端会打开 Vercel 的 OAuth 授权页面——点击允许后工具即可用。
- 验证 — 在 在线 Inspector 中粘贴
https://mcp.vercel.com并运行 initialize + tools/list 验证连通性。
🧰 工具预览(16)
| Tool | Safety | Description | Parameters |
|---|---|---|---|
| list_teams ~32 tok | 🟢 Read | List Vercel teams accessible to the user. | — |
| get_team ~29 tok | 🟢 Read | Get details of a Vercel team. | — |
| list_projects ~28 tok | 🟢 Read | List Vercel projects. | — |
| get_project ~30 tok | 🟢 Read | Get details of a Vercel project. | — |
| create_project ~30 tok | 🟠 Write | Create a new Vercel project. | — |
| list_deployments ~31 tok | 🟢 Read | List deployments of a project. | — |
| get_deployment ~30 tok | 🟢 Read | Get details of a deployment. | — |
| get_deployment_build_logs ~33 tok | 🟢 Read | Get build logs of a deployment. | — |
| deploy_to_vercel ~30 tok | 🟠 Write | Deploy a project to Vercel. | — |
| cancel_deployment ~31 tok | 🔴 Destructive | Cancel a running deployment. | — |
| list_domains ~27 tok | 🟢 Read | List Vercel domains. | — |
| get_domain ~28 tok | 🟢 Read | Get details of a domain. | — |
| list_env_vars ~33 tok | 🟢 Read | List environment variables of a project. | — |
| create_env_var ~32 tok | 🟠 Write | Create a project environment variable. | — |
| search_vercel_documentation ~33 tok | 🟢 Read | Search Vercel documentation. | — |
| delete_project ~29 tok | 🔴 Destructive | Delete a Vercel project. | — |
更多连接指南
GitHub MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Notion MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Linear MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Figma Dev Mode MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
AWS Knowledge → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Stripe MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →