Fetch

Provides web content fetching and HTML-to-markdown conversion to empower MCP clients to retrieve live web content.

javascript

0

GitHub Stars

javascript

Language

3 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "xinthedark-mcp_server_fetch2": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}

Fetch MCP Server provides web content fetching capabilities, turning HTML pages into markdown so you can easily summarize, transform, and cite live web sources within your conversations and prompts.

How to use

You integrate the Fetch MCP Server with your MCP client to retrieve and convert web content on demand. Use the fetch tool to pull a page, convert it to markdown, and then continue your analysis or compose responses with the extracted content. You can read the page in chunks by starting from a specific index, which helps models locate exact information without loading the entire page at once.

How to install

Prerequisites depend on how you want to run the server.

Option A: Use uvx (recommended) to run the MCP server directly.

# Ensure you have uvx available, then run the MCP fetch server
uvx mcp-server-fetch

How to install

Option B: Install via Python using pip and run the module directly.

pip install mcp-server-fetch

python -m mcp_server_fetch

How to install

Option C: Run using Docker. This uses a prebuilt container for the fetch server.

docker run -i --rm mcp/fetch

Available tools

fetch

Fetch a URL and extract its contents as markdown, with optional max_length and start_index to read content in chunks.