mult-fetch-mcp-server logo

mult-fetch-mcp-server

by lmcc-dev

This project implements an MCP-compliant client and server for communication between AI assistants and external tools. It supports Standard Input/Output (Stdio) transport and provides multiple web scraping methods.

View on GitHub

Last updated: N/A

What is mult-fetch-mcp-server?

The mult-fetch-mcp-server is an MCP (Model Context Protocol) compliant server designed to facilitate communication between AI assistants and external tools, primarily for web scraping and content retrieval. It supports the Stdio transport method and offers various features for intelligent content extraction and management.

How to use mult-fetch-mcp-server?

The server can be installed globally or locally using pnpm or npx. To integrate with Claude desktop, you need to configure the claude_desktop_config.json file with the appropriate command and arguments. Once configured, you can use tools like fetch_html, fetch_json, etc., in your Claude conversations to retrieve and process web content.

Key features of mult-fetch-mcp-server

  • Implementation based on the official MCP SDK

  • Support for Standard Input/Output (Stdio) transport

  • Multiple web scraping methods (HTML, JSON, text, Markdown, plain text conversion)

  • Intelligent mode switching: automatic switching between standard requests and browser mode

  • Content size management: automatically splits large content into manageable chunks

  • Intelligent Content Extraction using Mozilla's Readability library

  • Metadata Support: Ability to extract webpage metadata

  • Smart Content Detection: Automatically detects if a page contains meaningful content

  • Browser Automation Enhancements: Support for page scrolling, cookie management, selector waiting

  • Bilingual internationalization (English and Chinese)

Use cases of mult-fetch-mcp-server

  • Retrieving HTML content from a webpage for AI analysis

  • Fetching JSON data from an API endpoint

  • Extracting plain text content from a website

  • Converting HTML content to Markdown format

  • Debugging website fetching issues using the debug mode

  • Using proxy settings to access websites behind firewalls

  • Extracting meaningful content from articles, filtering out ads and navigation

  • Automating browser interactions for websites requiring JavaScript execution

FAQ from mult-fetch-mcp-server

What is MCP?

MCP stands for Model Context Protocol, a standard for communication between AI assistants and external tools.

How do I install the server?

You can install it globally or locally using pnpm or npx. Refer to the Installation section in the README for detailed instructions.

How do I integrate this with Claude desktop?

You need to configure the claude_desktop_config.json file with the correct command and arguments. See the Integration with Claude section for examples.

How do I set the language?

Set the MCP_LANG environment variable to en for English or zh for Chinese.

How do I enable debug mode?

Set the debug: true parameter when calling a tool. Debug messages will be sent to stderr and a log file.