Fetch MCP Server
Fetch web pages and convert HTML to Markdown for AI consumption
The Fetch MCP Server is a lightweight tool that retrieves web pages and converts them to clean Markdown. Essential for research agents that need to read documentation, blog posts, or any web content in a format that LLMs understand efficiently.
Installation & Configuration
Add this block to your claude_desktop_config.json (or your agent framework's MCP config file):
{
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
}
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/claude/claude_desktop_config.json
Available Tools (1)
fetch
Use Cases
- Research — let Claude read any URL and summarize it
- Documentation access — agents fetch API docs on demand
- Content extraction — pull structured data from web pages
Source & Documentation
GitHub Repository: https://github.com/modelcontextprotocol/servers/tree/main/src/fetch
Protocol: Model Context Protocol (MCP) — modelcontextprotocol.io