Happy slice of mcp pizzaMCP.pizza

deepwiki-mcp

MCP.Pizza Chef: regenrek

Pages on DeepWiki hold generated documentation for open-source projects, and this connection fetches them, follows the links inside, strips out menus and ads, and returns tidy Markdown — either as one document or page by page. You can name a project instead of pasting a link. It accepts DeepWiki addresses only, needs no account, and installs with a short config block in Cursor, Cline or Windsurf. One caveat: the author warns it stopped working after DeepWiki blocked scraping, and points people to the official DeepWiki connection instead.

Doesn't work · stopped working after DeepWiki blocked scraping; use official DeepWiki server
Coding
Web/Research

Use This MCP server To

Pull a project's documentation into my editor as clean text Ask how a library works and get a current answer Fetch a single documentation page instead of a whole site Grab documentation by project name without hunting for links Read a project write-up without the site clutter

README

Deepwiki MCP Server

⚠️ IMPORTANT NOTICE: This server is currently not working since DeepWiki has cut off the possibility to scrape it. We recommend using the official DeepWiki MCP server at https://docs.devin.ai/work-with-devin/deepwiki-mcp for the time being.

This is an unofficial Deepwiki MCP Server

It takes a Deepwiki URL via MCP, crawls all relevant pages, converts them to Markdown, and returns either one document or a list by page.

Features

  • 🔒 Domain Safety: Only processes URLs from deepwiki.com
  • 🧹 HTML Sanitization: Strips headers, footers, navigation, scripts, and ads
  • 🔗 Link Rewriting: Adjusts links to work in Markdown
  • 📄 Multiple Output Formats: Get one document or structured pages
  • 🚀 Performance: Fast crawling with adjustable concurrency and depth
  • NLP: It's to search just for the library name

Usage

Prompts you can use:

deepwiki fetch how can i use gpt-image-1 with "vercel ai" sdk

deepwiki fetch how can i create new blocks in shadcn?

deepwiki fetch i want to understand how X works

Fetch complete Documentation (Default)

use deepwiki https://deepwiki.com/shadcn-ui/ui
use deepwiki multiple pages https://deepwiki.com/shadcn-ui/ui

Single Page

use deepwiki fetch single page https://deepwiki.com/tailwindlabs/tailwindcss/2.2-theme-system

Get by shortform

use deepwiki fetch tailwindlabs/tailwindcss

deepwiki fetch library

deepwiki fetch url
deepwiki fetch <name>/<repo>

deepwiki multiple pages ...
deepwiki single page url ...

Cursor

Add this to .cursor/mcp.json file.

{
  "mcpServers": {
    "mcp-deepwiki": {
      "command": "npx",
      "args": ["-y", "mcp-deepwiki@latest"]
    }
  }
}

Deepwiki Logo

deepwiki-mcp FAQ

Does it still work?
The author warns it stopped working once DeepWiki blocked scraping, and recommends the official DeepWiki connection from Devin instead.
Which apps does it work in?
Cursor, Cline and Windsurf are documented, and any assistant that accepts a local MCP connection can run it.
Do I need an account key?
No — it fetches public DeepWiki pages and there is nothing to sign in with.
Can I use this to learn how a library works?
That was the whole point — name the project and it collects the write-up so your assistant can answer from it.
Can it fetch other sites?
No — as a safety measure it accepts DeepWiki addresses only and refuses anything else.
How hard is setup?
A short config block pointing at the package, which most editors can run without installing anything first.