lmcc-dev/mult-fetch-mcp-server

本页由 AI 翻译，技术细节请以原文为准。查看原文

15 stars 10 forks 质量 86 趋势 41MIT

A versatile MCP-compliant web content fetching tool that supports multiple modes (browser/node), formats (HTML/JSON/Markdown/Text), and intelligent proxy detection, with bilingual interface...

概览

This project implements an MCP-compliant client and server for communication between AI assistants and external tools. Call the fetch tool with a URL. The default format is Markdown, using an HTTP fetch plus readable-article extraction. startCursor is not required. A normal page comes back in one response. The default budget is maxChars 100000 and maxBytes 1048576, and a cut prefers a newline or a space. When the body is longer, the response includes nextCursor and chunkId. Call fetch again with cursor set to nextCursor. fetch_html, fetch_json, fetch_txt, fetch_markdown, and fetch_plaintext are thin aliases of fetch with a fixed format. Add this to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project: - : ~/Library/Application Support/Claude/claude_desktop_config.json - : %APPDATA%/Claude/claude_desktop_config.json Restart the host after saving. Ask it to fetch a URL. It should call fetch without startCursor. The default HTTP fetcher does not need Chrome or Puppeteer.

README

以下为原文 README 节选，完整内容请查看原文。

mult-fetch-mcp-server

This project implements an MCP-compliant client and server for communication between AI assistants and external tools.

English | 中文文档

Version 2.0

在 GitHub 查看完整 README

安装

npx -y @lmcc-dev/mult-fetch-mcp-server

新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "mult-fetch": {
      "command": "npx",
      "args": ["-y", "@lmcc-dev/mult-fetch-mcp-server"],
      "env": {
        "MCP_LANG": "en"
      }
    }
  }
}