Fetch MCP Server with CSS selectors function

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

FAQ from Fetch MCP Server with CSS selectors function

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.