Deepwiki MCP Server

Name: Deepwiki MCP Server
Author: instructa

@instructa

リポジトリ

Deepwiki MCP Server について

A MCP Server that gives you latest docs and data from the web

#deepwiki #mcp-server #data-fetcher

基本情報

カテゴリ

その他

ライセンス

MIT license

ランタイム

node

トランスポート

stdio

公開者

instructa

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "nowledge": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp-deepwiki",
        "."
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Deepwiki MCP Server?

Deepwiki MCP Server is an unofficial MCP server that takes a Deepwiki URL, crawls all relevant pages, converts them to Markdown, and returns either a single aggregated document or a structured list of pages. It is designed for developers who want to extract documentation from deepwiki.com repositories for use with AI tools and coding assistants.

How to use Deepwiki MCP Server?

Configure it in your MCP client (e.g., Cursor) by adding mcp-deepwiki to .cursor/mcp.json with the command npx -y mcp-deepwiki@latest. Then use prompts like deepwiki fetch <query>, use deepwiki <url>, or call the registered deepwiki_fetch tool with parameters url (required), mode (aggregate or pages), and maxDepth (optional, default 10).

Key features of Deepwiki MCP Server

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: single aggregated document or structured pages.
Fast crawling with adjustable concurrency and depth.
NLP support for searching by library name.

Use cases of Deepwiki MCP Server

Fetch complete documentation of a Deepwiki repository as one Markdown file.
Retrieve specific pages from a Deepwiki repo in a structured list.
Quickly understand how a library or tool works by crawling its Deepwiki docs.
Integrate Deepwiki documentation into AI coding assistants like Cursor for inline reference.

FAQ from Deepwiki MCP Server

What domains does Deepwiki MCP Server accept?

Only URLs from deepwiki.com are allowed. Any other domain will return a DOMAIN_NOT_ALLOWED error.

What output formats are available?

Two modes: aggregate (default) returns a single Markdown document with all pages concatenated; pages returns an array of objects each containing path and markdown.

How can I adjust crawling performance?

Set environment variables: DEEPWIKI_MAX_CONCURRENCY (default 5), DEEPWIKI_REQUEST_TIMEOUT (default 30000 ms), DEEPWIKI_MAX_RETRIES (default 3), and DEEPWIKI_RETRY_DELAY (default 250 ms).

What happens if some pages fail to crawl?

The server may return a partial success response with a status of partial, including successfully fetched data and a list of errors with URLs and reasons.

Does Deepwiki MCP Server emit progress events?

Yes, during crawling the tool sends progress events showing each fetched URL, byte size, request time, and HTTP status.

「その他」の他のコンテンツ

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K