MCP-webfetch
A web fetching MCP server with HTTP proxy support, allowing AI to retrieve web content in markdown, text, or HTML format while handling anti-crawler detection and redirects.
README
MCP-webfetch
通过 SOCKS5 代理抓取网页内容的 MCP 服务器。基于 opencode 官方 webfetch 实现,添加了代理支持。
功能
- 通过
127.0.0.1:10808SOCKS5 代理获取网页 - 支持格式:markdown(默认)、text、html
- HTML→Markdown 转换(TurndownService)
- HTML→Text 提取(htmlparser2)
- 自动跟进重定向(防循环检测)
- Cloudflare 反爬检测 + 自动重试
- MIME 类型校验(图片/二进制自动拒绝)
- Body 大小限制(5MB)
安装
# 1. 克隆或复制本目录
cd D:\workplace\MCP-webfetch
# 2. 安装依赖(htmlparser2 + turndown)
npm install
配置 opencode
在 opencode.json 中添加:
{
"mcp": {
"webfetch-proxy": {
"type": "local",
"command": ["node", "D:\\workplace\\MCP-webfetch\\webfetch-proxy.js"],
"enabled": true
}
},
"permission": {
"webfetch": "deny"
}
}
- 项目级: 当前目录下的
opencode.json - 全局级:
~/.config/opencode/opencode.json
禁止内置 webfetch(可选)
在 permission 中设置 webfetch: "deny",让 AI 只能使用本 MCP 工具。
{
"permission": {
"webfetch": "deny"
}
}
配置代理地址
编辑 webfetch-proxy.js 顶部:
const PROXY_HOST = "127.0.0.1";
const PROXY_PORT = 10808;
重启 opencode
每次修改配置后需要重启 opencode 生效。
测试
node -e "
const { spawn } = require('child_process');
const proc = spawn('node', ['D:\\\\workplace\\\\MCP-webfetch\\\\webfetch-proxy.js']);
proc.stdin.write(JSON.stringify({jsonrpc:'2.0',id:1,method:'initialize',params:{protocolVersion:'2024-11-05',capabilities:{},clientInfo:{name:'t',version:'1'}}})+'\n');
setTimeout(() => {
proc.stdin.write(JSON.stringify({jsonrpc:'2.0',id:2,method:'tools/call',params:{name:'webfetch',arguments:{url:'https://httpbin.org/get',format:'text',timeout:5}}})+'\n');
}, 500);
setTimeout(() => { proc.kill(); process.exit(); }, 5000);
proc.stdout.on('data', (d) => { console.log(d.toString()); });
"
依赖
effect— 函数式运行时(HttpClient、Stream、Effect)htmlparser2— HTML 解析(文本提取)socks-proxy-agent— SOCKS5 代理客户端turndown— HTML→Markdown 转换
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.