Fetch

Fetch

By modelcontextprotocol GitHub

Web content fetching and conversion for efficient LLM usage

web-fetching llm-tools
Overview

What is Fetch?

Fetch is a Model Context Protocol (MCP) server designed for web content fetching and conversion, allowing Large Language Models (LLMs) to retrieve and process content from web pages by converting HTML into markdown for easier consumption.

How to use Fetch?

To use Fetch, install it via node.js or pip, and then run the server using the command: python -m mcp_server_fetch or with uvx as specified in the documentation. You can fetch content by calling the fetch tool with a URL.

Key features of Fetch?

  • Fetches web URLs and extracts their content in markdown format.
  • Supports configuration options such as maximum length of content and starting index for extraction.
  • Customizable user-agent and robots.txt compliance settings.

Use cases of Fetch?

  1. Enabling LLMs to access and process data from web pages for various applications.
  2. Converting online articles into a simplified format for analysis.
  3. Assisting in data retrieval tasks for research and data aggregation workflows.

FAQ from Fetch?

  • Can Fetch handle all types of web content?

Fetch is capable of extracting content from most web pages, although results may vary based on the site's structure and restrictions.

  • Is Fetch easy to integrate with other tools?

Yes! Fetch is designed to integrate smoothly with LLMs and can be customized to meet specific needs.

  • Is there any usage limit for Fetch?

Fetch does not impose strict usage limits, but your implementation may be subject to the guidelines of the websites you access.

Content

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.

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

Installation

Optionally: Install node.js, this will cause the fetch server to use a different HTML simplifier that is more robust.

When using uv no specific installation is needed. We will use uvx to directly run mcp-server-fetch.

Using PIP

Alternatively you can install mcp-server-fetch via pip:

pip install mcp-server-fetch

After installation, you can run it as a script using:

python -m mcp_server_fetch

Configuration

Configure for Claude.app

Add to your Claude settings:

Using uvx 
"mcpServers": {
  "fetch": {
    "command": "uvx",
    "args": ["mcp-server-fetch"]
  }
}
Using docker 
"mcpServers": {
  "fetch": {
    "command": "docker",
    "args": ["run", "-i", "--rm", "mcp/fetch"]
  }
}
Using pip installation 
"mcpServers": {
  "fetch": {
    "command": "python",
    "args": ["-m", "mcp_server_fetch"]
  }
}

Customization - robots.txt

By default, the server will obey a websites robots.txt file if the request came from the model (via a tool), but not if the request was user initiated (via a prompt). This can be disabled by adding the argument --ignore-robots-txt to the args list in the configuration.

Customization - User-agent

By default, depending on if the request came from the model (via a tool), or was user initiated (via a prompt), the server will use either the user-agent

ModelContextProtocol/1.0 (Autonomous; +https://github.com/modelcontextprotocol/servers)

or

ModelContextProtocol/1.0 (User-Specified; +https://github.com/modelcontextprotocol/servers)

This can be customized by adding the argument --user-agent=YourUserAgent to the args list in the configuration.

Debugging

You can use the MCP inspector to debug the server. For uvx installations:

npx @modelcontextprotocol/inspector uvx mcp-server-fetch

Or if you've installed the package in a specific directory or are developing on it:

cd path/to/servers/src/fetch
npx @modelcontextprotocol/inspector uv run mcp-server-fetch

Contributing

We encourage contributions to help expand and improve mcp-server-fetch. Whether you want to add new tools, enhance existing functionality, or improve documentation, your input is valuable.

For examples of other MCP servers and implementation patterns, see: https://github.com/modelcontextprotocol/servers

Pull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements to make mcp-server-fetch even more powerful and useful.

License

mcp-server-fetch is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Tools

fetch

Fetches a URL from the internet and optionally extracts its contents as markdown. Although originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.
No content found.