Fetch MCP Server

What it does

One of the official MCP reference servers. It gives the agent a single fetch tool that downloads a web page and converts the HTML to markdown, and it can read long pages in chunks. By default it refuses private and loopback addresses and follows robots.txt for requests the model makes.

Who it's for

Anyone who wants their agent to read a docs page, changelog or article by URL without a full browser.

How to set it up

1. Install uv (recommended); uvx then runs the server with no separate install.

2. Add to your MCP client config:

   jsonCopy

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

3. Or install with pip and run it as a module:

   bashCopy

   pip install mcp-server-fetch
   python -m mcp_server_fetch

4. Optional: install Node.js too; the server then uses a more robust HTML simplifier. The --allow-private-ips flag turns off the private-address guard, so only use it if you understand the risk.

Check the official Fetch MCP Server docs for the latest steps.

Example prompts

Fetch https://nextjs.org/docs and summarize what's new on that page.

Read this changelog URL and list the breaking changes.

Fetch this article and give me the 5 key points.

Demo