Fetch MCP Server with CSS selectors function

@burnworks

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

burnworks

关于 Fetch MCP Server with CSS selectors function

暂无概览

#fetch #mcp-server#web-content-fetching

Fetch MCP Server with CSS selectors function 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "burnworks-mcp-server-fetch": {
      "url": "https://example.com",
      "selector": "main-content",
      "selector_type": "id"
    }
  }
}

Fetch MCP Server with CSS selectors function 工具

Fetches a URL from the internet and extracts its contents as markdown.

概览

What is Fetch MCP Server with CSS selectors function?

Fetch MCP Server with CSS selectors function is a Model Context Protocol server that enables LLMs to fetch and extract web page content, converting HTML to markdown. It supports CSS, ID, and element selectors for targeted content extraction, and allows chunked reading of large pages.

How to use Fetch MCP Server with CSS selectors function?

Install using uvx (recommended) or pip. Configure in Claude.app by adding an MCP server entry with command uvx burnworks-mcp-server-fetch or python -m burnworks_mcp_server_fetch. Use the custom-fetch tool with parameters like url, max_length, start_index, raw, selector, and selector_type.

Key features of Fetch MCP Server with CSS selectors function

Fetches web pages and converts to markdown
Supports CSS, ID, and element selectors
Reads large pages in chunks with start_index
Returns raw content optionally
Respects or ignores robots.txt
Configurable user-agent and proxy

Use cases of Fetch MCP Server with CSS selectors function

Extracting main article content from news websites
Focusing on specific sections of documentation pages
Targeting specific content from large web pages using selectors
Reading a webpage in chunks to find needed information

常见问题

Does this server require Node.js?

Installing Node.js is optional; it makes the HTML simplifier more robust but is not required.

How do I handle truncated responses?

Use the `start_index` parameter to read content in chunks, specifying where to start extraction.

Can I extract specific parts of a page?

Yes, use `selector` and `selector_type` with values 'css', 'id', or 'element' to target specific content.

How do I configure robots.txt behavior?

By default, the server obeys robots.txt for tool requests but not prompt requests. Use `--ignore-robots-txt` to disable compliance.

浏览器自动化分类下的更多 MCP 服务器

BrowserTools MCP

AgentDeskAI

Monitor browser logs directly from Cursor and other MCP compatible IDEs.

7.3K

Full Self Browsing

Lakshman Turlapati

DOM-first AI browser automation for Chrome and MCP clients.

194

HTML/CSS to Image

An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.

Screenshot Scout

screenshotscout

Capture screenshots of webpages as images or PDFs with Screenshot Scout.

Fastcrw

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

286