Fetch: Streamline & Supercharge LLM Workflows

Fetch: Streamline web content fetching & conversion to supercharge LLM efficiency. Unlock insights faster, smarter, seamless.

Visit Repository

✨ Browser Automation

4.9(56 reviews)

84 saves

39 comments

Ranked in the top 3% of all AI tools in its category

About Fetch

What is Fetch: Streamline & Supercharge LLM Workflows?

Imagine your Large Language Model (LLM) trying to read a webpage and getting stuck in a maze of HTML tags like a confused goldfish in a labyrinth. That’s where Fetch steps in—like a superhero armed with a markdown wand. This MCP Server doesn’t just fetch URLs; it slices, dices, and converts web content into LLM-friendly chunks. Think of it as the Swiss Army knife of LLM data prep, handling everything from “I need just the first paragraph” to “Give me the raw HTML but make it faster.”

How to use Fetch: Streamline & Supercharge LLM Workflows?

Let’s say your LLM wants to analyze a product review site but keeps tripping over CSS styles. Here’s the play-by-play:

Install Fetch via your favorite method: UV for speed freaks, pip for the casual user, or Docker if you’re into containerized chaos.
Configure it like a pro. For example, setting up start_index=500 skips the first 500 bytes—perfect for avoiding those pesky intro paragraphs.
Watch as Fetch serves up markdownified content so clean, your LLM will start composing sonnets about it.

Pro tip: Pair with Claude for maximum synergy. Just ask it nicely.

Fetch Features

Key Features of Fetch: Streamline & Supercharge LLM Workflows?

Chunk Control: Auto-truncates responses but lets you pick where to start—like skipping to the good part of a Netflix episode.
Format Flexibility: Serve raw HTML (for those retro days) or markdown (for readability enthusiasts).
Configurable Safeguards: Tweak robots.txt rules and user-agent strings to avoid getting IP-banned by paranoid websites.

Think of it as the “Settings” menu for your LLM’s web browsing habits.

Use Cases of Fetch: Streamline & Supercharge LLM Workflows?

1. E-commerce Price Watchers: “Show me only the product price from this page—no ads, just numbers.”
2. Academic Researchers: “Extract every citation from this 50-page PDF-like website without the fluff.”
3. Real-Time Info Junkies: “Fetch the latest stock ticker from Yahoo Finance but skip the 10 paragraphs about their new CEO.”

Oh, and let’s not forget: saving your LLM from existential crisis

Fetch FAQ

FAQ from Fetch: Streamline & Supercharge LLM Workflows?

Q: Will Fetch work with my grandma’s dial-up connection?
A: Probably not, but it’s optimized for speeds faster than a sloth on espresso. Try upgrading first.

Q: Can I make Fetch bypass robots.txt?
A: You can configure it, but we strongly recommend respecting website rules. We’re not that kind of tool.

Q: Why does the output look like a markdown vampire?
A: Because it’s “draining the HTML” out of webpages. Get it? Draining… vampir—never mind.

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.

Using uv (recommended)

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)

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.