Deepwiki MCP ServerServer

regenrek
GitHub
web scrapingmarkdown conversionNLP

Loading subscription status...

💡 Description

This is an unofficial Deepwiki MCP server that accepts Deepwiki URLs via MCP, crawls all the related pages, and returns them as Markdown, either as a single document or a list per page.

📝 JSON Entries

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

🛠️ Tools

deepwiki_fetch

Features

  • Domain safety: only processes URLs from deepwiki.org
  • HTML sanitization: removes headers, footers, navigation, scripts, and ads
  • Link rewriting: adjusts links to work with Markdown
  • Multiple output formats: either a single document or structured page data
  • Performance: fast crawling with adjustable concurrency and depth
  • NLP: searches by library name only

💬 Example Queries

  • 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