XFetch MCP Server
by xfetchai
XFetch MCP Server is an enhanced Model Context Protocol server for fetching web content, designed to bypass security systems like Cloudflare. It enables LLMs to retrieve and process content from any web pages, including dynamic websites.
Last updated: N/A
What is XFetch MCP Server?
XFetch MCP Server is a tool that allows Large Language Models (LLMs) to fetch and process content from web pages, even those protected by security systems or requiring JavaScript rendering. It acts as a bridge between LLMs and the web, providing a way to access information that would otherwise be inaccessible.
How to use XFetch MCP Server?
- Install the server using pip or uv.
- Configure your LLM (e.g., Claude) to use the XFetch MCP server, providing the command and arguments.
- Obtain an API token for commercial use from xfetch.ai and configure it via environment variable, command-line argument, or Claude configuration.
- Send requests to the server with the URL and optional parameters like 'render', 'selector', 'timeout', 'max_length', and 'start_index'.
Key features of XFetch MCP Server
Bypass Protection Systems
JavaScript Rendering
CSS Selectors
Dynamic Content Loading
Markdown Conversion
Chunked Reading
Use cases of XFetch MCP Server
Fetching content from websites protected by Cloudflare
Extracting specific information from dynamic web pages
Providing LLMs with up-to-date information from the web
Summarizing long articles by reading them in chunks
FAQ from XFetch MCP Server
What is the default API token for?
What is the default API token for?
The default API token is for testing, evaluation, personal projects, and small-scale non-commercial use.
How do I get a commercial API token?
How do I get a commercial API token?
Visit xfetch.ai to register for a commercial account and get your dedicated API token.
How do I configure the API token?
How do I configure the API token?
You can configure the API token via environment variable (XFETCH_API_TOKEN), command-line argument (--api-token), or in your Claude configuration.
What are the available tools?
What are the available tools?
The main tool is xfetch, which accepts parameters like url, max_length, start_index, raw, render, selector, and timeout.
How do I debug the server?
How do I debug the server?
You can use the MCP inspector with the command: npx @modelcontextprotocol/inspector uvx mcp-server-xfetch.