Fetch-MCP：基于Playwright的MCP服务器，支持批量URL抓取

Fetch-MCP：基于Playwright的MCP服务器，支持批量URL抓取
Fetch-MCP: Playwright-Based MCP Server with Batch URL Fetching Support

原始链接: https://github.com/jae-jae/fetch-mcp

使用 Playwright 无头浏览器获取网页内容的 MCP 服务器。直接使用 npx 运行：`npx -y github:jae-jae/fetch-mcp`。使用 `--debug` 选项运行以显示浏览器窗口进行调试：`npx -y github:jae-jae/fetch-mcp --debug`。在 Claude Desktop 中配置此 MCP 服务器： * macOS：~/Library/Application Support/Claude/claude_desktop_config.json * Windows：%APPDATA%/Claude/claude_desktop_config.json 配置文件内容： ```json { "mcpServers": { "fetch": { "command": "npx", "args": ["-y", "github:jae-jae/fetch-mcp"] } } } ``` 安装 Playwright 浏览器：安装 Playwright 所需的浏览器。使用 MCP Inspector 进行调试：您也可以启用可见浏览器模式进行调试：`node build/index.js --debug`

Fetch-MCP是一个基于Playwright构建的网页内容抓取服务器，旨在高效地获取静态和动态网页内容。它提供`fetch_url`用于单页抓取，以及`fetch_urls`用于高性能并行批量抓取多个URL。它可以提取网页的主要内容，并支持Markdown转换。Fetch-MCP易于配置，是一个强大且可扩展的网页抓取解决方案，适合开发者使用。

Show HN: Codemcp – Claude Pro用户专享的Claude代码工具 – 告别API账单 2025-03-19

Show HN：MCP-Kafka——Kafka命令的自然语言接口 2025-03-20

（评论） 2025-03-19

（评论） 2024-08-08

原文

MCP server for fetch web page content using Playwright headless browser.

Run directly with npx:

npx -y github:jae-jae/fetch-mcp

Run with the --debug option to show the browser window for debugging:

npx -y github:jae-jae/fetch-mcp --debug

Configure this MCP server in Claude Desktop:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": ["-y", "github:jae-jae/fetch-mcp"]
    }
  }
}

Install Playwright Browser

Install the browsers needed for Playwright:

Use MCP Inspector for debugging:

You can also enable visible browser mode for debugging:

node build/index.js --debug

Fetch-MCP：基于Playwright的MCP服务器，支持批量URL抓取 Fetch-MCP: Playwright-Based MCP Server with Batch URL Fetching Support

Install Playwright Browser

Fetch-MCP：基于Playwright的MCP服务器，支持批量URL抓取
Fetch-MCP: Playwright-Based MCP Server with Batch URL Fetching Support