What is Fetch MCP Server

Fetch is a Model Context Protocol (MCP) server designed for web content fetching and conversion, enabling efficient interaction with large language models (LLMs). It allows LLMs to access and manipulate web data seamlessly, providing a structured way to retrieve and process online content.

Use cases

Fetch can be utilized for various applications such as extracting information from web pages, converting web content into formats suitable for LLM processing, and automating data retrieval tasks. It is particularly useful in scenarios that require real-time data access, web scraping, and content aggregation.

How to use

To use Fetch, you can start the server using the command 'npx -y @modelcontextprotocol/server-fetch'. After starting the server, configure your LLM client (like Claude Desktop) to connect to Fetch by specifying the server command and any necessary arguments in the MCP server configuration.

Key features

Fetch offers several key features including the ability to fetch and convert web content dynamically, support for various output formats, and integration capabilities with LLM clients. It is designed to handle complex web interactions while ensuring ease of use and flexibility.

Where to use

Fetch is ideal for environments where LLMs need to interact with web data, such as research applications, content curation tools, and automated reporting systems. It can be deployed in various settings including academic research, business intelligence, and content management systems.

Fetch MCP Server

A Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.

[!CAUTION]
This server can access local/internal IP addresses and may represent a security risk. Exercise caution when using this MCP server to ensure this does not expose any sensitive data.

The fetch tool will truncate the response, but by using the start_index argument, you can specify where to start the content extraction. This lets models read a webpage in chunks, until they find the information they need.

Available Tools

• fetch - Fetches a URL from the internet and extracts its contents as markdown.
  • url (string, required): URL to fetch
  • max_length (integer, optional): Maximum number of characters to return (default: 5000)
  • start_index (integer, optional): Start content from this character index (default: 0)
  • raw (boolean, optional): Get raw content without markdown conversion (default: false)

Prompts

• fetch
  • Fetch a URL and extract its contents as markdown
  • Arguments:
    • url (string, required): URL to fetch

Local

{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}

Remote

{
  "mcpServers": {
    "fetch": {
      "type": "streamable-http",
      "url": "https://router.mcpso.cc/mcp/fetch"
    }
  }
}