Skip to main content
MCP server CX Codex

Defuddle Fetch — Claude Code MCP server: what it does, how to install

Downloads a web page by URL and gives the agent clean markdown with title, author and date. Handy when the agent has to read docs or an article.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add defuddle-fetch-mcp-server -- npx -y defuddle-fetch-mcp-server
Open on GitHub

What Defuddle Fetch does

The server adds a single tool, fetch. Give it a url and it downloads the page, strips the surrounding clutter with Defuddle and hands back the main text as markdown, together with title, author, publication date, word count, domain and processing time.

It is built as a replacement for the stock fetch server that relies on Readability, and the author says Defuddle copes better with most modern pages. Set raw to true if you want the page content without markdown conversion.

Only 5000 characters come back by default, so a long article has to be read in slices: start_index sets the offset and max_length the slice size. It launches through npx, which means Node.js must be installed.

What it helps with

  • read a docs page or article from a link inside the agent chat
  • pull the author and publication date out of a page
  • read a long page in slices by moving start_index
  • get the original HTML when markdown is the wrong format
  • swap the stock Readability-based fetch server for a cleaner one

Example prompts for the agent

  • Use defuddle-fetch to read the article at the link above and tell me who wrote it and when
  • Fetch the next slice of the same page with fetch, starting at index 5000
  • Grab this page through defuddle-fetch with raw on, I need the HTML

How to install Defuddle Fetch

Platform CLI

claude mcp add defuddle-fetch-mcp-server -- npx -y defuddle-fetch-mcp-server

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Defuddle Fetch

How do I install Defuddle Fetch in Claude Code?

Run claude mcp add defuddle-fetch-mcp-server -- npx -y defuddle-fetch-mcp-server. A shorter server name works too: claude mcp add defuddle-fetch -- npx -y defuddle-fetch-mcp-server.

What does Defuddle Fetch do?

It loads a page by URL, cleans it with Defuddle and returns the main text as markdown plus metadata such as title, author, publication date, word count and domain.

How is Defuddle Fetch different from the default fetch server?

It can replace the default one directly, but cleans pages with Defuddle instead of Readability. The author says this gives better results on most modern pages.

Similar MCP servers

All MCP servers for Browser and scraping →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor