Fetch MCP Server

@zcaceres

代码仓库

基本信息

分类

浏览器自动化

许可证

MIT

传输方式

stdio

作者

zcaceres

关于 Fetch MCP Server

A flexible HTTP fetching Model Context Protocol server.

#fetch #web-content #data-fetching

Fetch MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "fetch-mcp-zcaceres": {
      "command": "npx",
      "args": [
        "mcp-fetch",
        "<command>",
        "<url>",
        "[flags]"
      ]
    }
  }
}

Fetch MCP Server 工具

Perform HTTP requests with full control over method, headers, body, and other fetch options

Get use cases and best practices for using the tools in this MCP server

Execute GraphQL queries and mutations with support for variables and custom headers

Control browsers and pages with Puppeteer - launch/close browsers, open/close pages, execute JavaScript, take screenshots, and more

Manage WebSocket connections - connect, send, receive messages, list connections, and close

概览

What is Fetch MCP Server?

Fetch MCP Server is an MCP (Model Context Protocol) server that fetches web content and returns it in multiple formats: HTML, JSON, plain text, Markdown, readable article content (via Mozilla Readability), and YouTube video transcripts. It is intended for AI agents and developers who need to programmatically retrieve and process web content.

How to use Fetch MCP Server?

Install with npx mcp-fetch-server or globally via npm install -g mcp-fetch-server. Add it as an MCP server in your client configuration under "mcpServers", or use the CLI: mcp-fetch <command> <url> [flags]. Commands include html, markdown, readable, txt, json, and youtube. All tools accept common parameters: url, headers, max_length, start_index, and proxy.

Key features of Fetch MCP Server

Fetch web content as HTML, JSON, plain text, or Markdown
Extract article content with Mozilla Readability (strips ads, nav, boilerplate)
Extract YouTube video transcripts (via yt-dlp or direct extraction)
Proxy support for requests behind firewalls
SSRF protection (blocks private/localhost addresses and DNS rebinding)
Response size limits and configurable character limit via environment variables

Use cases of Fetch MCP Server

An AI agent fetching a webpage to answer user questions about its content
Extracting the main article from a news or blog post, free of ads and navigation
Retrieving JSON from an API endpoint for structured data processing
Obtaining a YouTube video transcript for summarization or translation
Browsing web pages with custom headers or through a proxy in restricted networks

常见问题

What content formats does Fetch MCP Server support?

It supports HTML, Markdown, plain text, JSON, readable article content (Markdown via Mozilla Readability), and YouTube transcripts.

How can I set a custom character limit for responses?

Use the `max_length` parameter in the tool call, or set the `DEFAULT_LIMIT` environment variable (default 5000 characters; 0 for no limit).

Does Fetch MCP Server support proxy requests?

Yes. Pass the `proxy` parameter (e.g., `http://proxy:8080`) to route requests through a proxy.

Is there protection against SSRF attacks?

Yes. The server blocks requests to private/localhost addresses and implements DNS rebinding protection.

Can I get YouTube transcripts with a specific language?

Yes. Use the `youtube` command or `fetch_youtube_transcript` tool with the optional `lang` parameter (default `"en"`).

浏览器自动化分类下的更多 MCP 服务器

Scrapling Fetch MCP

cyberchitta

Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.

101