Fetch MCP Server with CSS selectors function
by burnworks
This is a Model Context Protocol server that fetches web content and converts HTML to markdown, enabling LLMs to process web pages. It includes a powerful selector feature that allows you to extract specific content from web pages.
Last updated: N/A
What is Fetch MCP Server with CSS selectors function?
The Fetch MCP Server is a tool that allows LLMs to retrieve and process content from web pages. It converts HTML to markdown for easier consumption by language models and includes a selector feature to extract specific content.
How to use Fetch MCP Server with CSS selectors function?
Install the server using uv or pip. Configure it in your Claude settings. Use the custom-fetch tool with the url, selector, and selector_type arguments to extract specific content from web pages. The server can be customized with arguments like --ignore-robots-txt, --user-agent, and --proxy-url.
Key features of Fetch MCP Server with CSS selectors function
Fetches web content
Converts HTML to markdown
CSS selector functionality
ID selector functionality
Element selector functionality
Customizable user-agent
Proxy support
robots.txt handling
Use cases of Fetch MCP Server with CSS selectors function
Extract main article content from news sites
Focus on specific sections of documentation pages
Target precisely the content you need from large web pages
Retrieve data for LLM analysis
Automated web content extraction
FAQ from Fetch MCP Server with CSS selectors function
What is the default maximum length of the fetched content?
What is the default maximum length of the fetched content?
The default maximum length is 5000 characters.
How do I specify which part of the content to extract?
How do I specify which part of the content to extract?
Use the selector and selector_type arguments to specify a CSS selector, ID, or element name.
What selector types are supported?
What selector types are supported?
The server supports 'css', 'id', and 'element' selector types.
How can I ignore the robots.txt file?
How can I ignore the robots.txt file?
Add the argument --ignore-robots-txt to the args list in the configuration.
How do I set up a proxy?
How do I set up a proxy?
Use the --proxy-url argument to specify the proxy URL.