Token导航 LogoToken导航TokenDH.com
研究检索可写文件clawhub未标认证来源可访问clear审计通过

mcp-vercelMCP Vercel 搜索

Agent Skill

mcp-vercel 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,410

周安装

221

GitHub Stars

公开资料未说明

下载量

1,750
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:mcp-vercel(MCP Vercel 搜索)
来源仓库:https://github.com/lucaperret/mcp-vercel
安装命令:
openclaw skills install mcp-vercel
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install mcp-vercel

简介

使用 Next.js 和 mcp-handler 在 Vercel 平台部署远程 MCP 服务器。

  • 适合需要云端托管 MCP 服务或实现跨地域访问的用户。
  • 自动完成项目初始化、构建配置和部署流程,支持自定义域名。
  • 需准备 Vercel 账号并配置相关环境变量,注意计费模式可能产生费用。
  • 建议提前规划服务器功能和访问权限,确保符合平台安全策略。

SKILL.md

name
mcp-vercel
description
Deploy a remote MCP server on Vercel with Next.js and mcp-handler. Use this skill whenever the user wants to create an MCP server, deploy MCP to Vercel, set up a remote MCP endpoint, add MCP tools to a Next.js app, or host an MCP server in the cloud. Also triggers on: 'deploy MCP', 'remote MCP', 'MCP endpoint', 'mcp-handler', 'MCP on Vercel', 'Streamable HTTP MCP', 'Claude connector backend', 'host MCP server for Claude Desktop'. Even if the user just says 'I want to make my API available to Claude' or 'set up an MCP server', use this skill.
license
MIT
metadata
author
lucaperret
version
1.0.0
openclaw
emoji
\▲
homepage
https://github.com/lucaperret/agent-skills

Deploy MCP Server on Vercel

Create a production-ready remote MCP server on Vercel using Next.js and mcp-handler. The server communicates via Streamable HTTP and works with Claude Desktop, claude.ai, Smithery, and any MCP client.

Why this approach

Vercel's serverless functions are ideal for MCP servers because MCP's Streamable HTTP transport is stateless — each request is independent, which maps perfectly to serverless. No persistent connections needed. The mcp-handler package from Vercel handles all the protocol details.

Quick setup

1. Install dependencies

npm install mcp-handler @modelcontextprotocol/sdk zod

2. Create the MCP route

Create app/api/mcp/route.ts:

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { createMcpHandler } from 'mcp-handler';
import { z } from 'zod';

const handler = createMcpHandler(
  (server: McpServer) => {
    // Register your tools here
    server.tool(
      'example_tool',
      'What this tool does — be specific',
      { query: z.string().describe('What the parameter is for') },
      { readOnlyHint: true, destructiveHint: false, title: 'Example Tool' },
      async ({ query }) => ({
        content: [{ type: 'text', text: `Result for: ${query}` }],
      }),
    );
  },
  {
    serverInfo: { name: 'my-server', version: '1.0.0' },
  },
  {
    streamableHttpEndpoint: '/api/mcp',
    maxDuration: 60,
  },
);

export { handler as GET, handler as POST, handler as DELETE };

3. Deploy and test

vercel deploy --prod

# Verify
curl -X POST https://your-app.vercel.app/api/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}},"id":1}'

You should get back serverInfo with your server name and version.

Tool design

Safety annotations (required)

Every tool must have annotations. MCP clients use these to decide how cautiously to invoke tools.

// Read-only (search, get, list, fetch)
{ readOnlyHint: true, destructiveHint: false, title: 'Search Items' }

// Write but not destructive (create, add, update)
{ readOnlyHint: false, destructiveHint: false, title: 'Create Item' }

// Destructive (delete, remove, overwrite)
{ readOnlyHint: false, destructiveHint: true, title: 'Delete Item' }

Parameter descriptions

Every parameter needs a .describe() — this is how MCP clients know what to pass.

{
  query: z.string().describe('Search query text'),
  limit: z.number().optional().default(10).describe('Max results to return'),
  type: z.enum(['artist', 'album', 'track']).describe('Type of content'),
}

MCP prompts (optional but recommended)

Prompt templates improve discoverability on Smithery and give users ready-made starting points.

server.prompt('find_items', 'Search for items by name',
  { name: z.string().describe('Item name') },
  ({ name }) => ({
    messages: [{
      role: 'user' as const,
      content: { type: 'text' as const, text: `Find ${name} and show details` },
    }],
  }),
);

Routing — the streamableHttpEndpoint gotcha

Use streamableHttpEndpoint, NOT basePath:

// CORRECT — endpoint at /api/mcp
{ streamableHttpEndpoint: '/api/mcp' }

// WRONG — creates endpoint at /api/mcp/mcp (doubled path)
{ basePath: '/api/mcp' }

The basePath option appends /mcp to whatever you give it. Since your route file is already at app/api/mcp/route.ts, that creates /api/mcp/mcp.

Vercel deployment pitfalls

Root Directory isolation

If your Vercel project uses a Root Directory (like site/), the deployed function CANNOT access files outside that directory. This means import from '../../dist/' will fail at runtime even if it compiles locally.

Solution: Copy compiled files into the site directory and commit them. Use a prebuild script to keep them in sync:

// scripts/copy-deps.js
const fs = require('fs');
const path = require('path');
const src = path.resolve(__dirname, '../../dist');
const dest = path.resolve(__dirname, '../lib/deps');
fs.mkdirSync(dest, { recursive: true });
for (const file of fs.readdirSync(src)) {
  if (file.endsWith('.js') || file.endsWith('.d.ts')) {
    fs.copyFileSync(path.join(src, file), path.join(dest, file));
  }
}

Add to package.json: "prebuild": "node scripts/copy-deps.js"

Serverless read-only filesystem

Vercel functions run on a read-only filesystem with no home directory. If your code writes files (sessions, temp data), wrap in try/catch:

try {
  fs.mkdirSync(dir, { recursive: true });
  fs.writeFileSync(filepath, data);
} catch {
  // Serverless environment — skip filesystem writes
}

Turbopack CJS/ESM mismatch

If importing CommonJS .js files while the parent package.json doesn't have "type": "module", Turbopack will error. Solution: import from compiled .js files bundled within the site directory, not from TypeScript source files in the parent.

Adding authentication

For OAuth-protected servers, see the mcp-oauth skill which covers the complete OAuth 2.0 PKCE flow with withMcpAuth, including dynamic client registration and token storage.

Publishing to Smithery

After deploying, publish to Smithery for broader distribution:

  1. Go to https://smithery.ai/new
  2. Enter your MCP server URL
  3. Choose a namespace/server-id
  4. Smithery scans your tools automatically

If your server requires auth, Smithery will prompt you to connect during scanning.

Reference

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

85%
按下载量换算1,488

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

可写文件

该 Skill 可能写入或修改本地文件,使用前需要确认目标目录和修改范围。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills