Deepwiki MCP Server

Deepwiki repository content transformation into Markdown for AI agents.

Data last scanned today · Reviewed today

361 tool★ 1,375TypeScriptMIT

Overview

Deepwiki MCP Server enables AI agents to crawl, scrape, and convert Deepwiki documentation pages directly into Markdown format. It supports both aggregate outputs for full repository documentation and structured lists for individual page access, utilizing configurable crawl depth and concurrency settings.

Our verdict

This server carries a high risk level (36/100) and is currently non-functional because the target service has disabled scraping. The repository is community-maintained with no official affiliation, and several security-critical areas including OAuth and authentication methods remain unreviewed. Potential users are strongly advised to use the official DeepWiki MCP server provided by the vendor instead.

Supports customizable crawl depth and page aggregation
Provides built-in HTML sanitization for clean Markdown
Limited supply-chain surface with 24 direct dependencies

Functionality is blocked by target service restrictions
Security-critical features like OAuth remain unreviewed
Last code commit occurred over four months ago

Setup

Claude Desktop

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

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

Tool	Description	Risk
deepwiki_fetch	Crawls a Deepwiki repository and returns the content in Markdown format.	low

Compatibility

Client	Local	Docker	Remote	Read-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

›Is this server currently functional?

No, this server is currently not working because DeepWiki has blocked scraping. The project README recommends using the official DeepWiki MCP server instead.

›What domains can this server process?

For security reasons, the server only processes URLs originating from deepwiki.com.

›How can I adjust the crawling behavior?

You can configure crawling behavior using environment variables such as DEEPWIKI_MAX_CONCURRENCY, DEEPWIKI_REQUEST_TIMEOUT, DEEPWIKI_MAX_RETRIES, and DEEPWIKI_RETRY_DELAY.

›What output formats are available?

The server supports an 'aggregate' mode which returns a single Markdown document, and a 'pages' mode which returns structured page data.

›What should I do if I encounter EACCES errors?

If you receive a permission denied error, ensure the binary is executable by running chmod +x ./node_modules/.bin/mcp-deepwiki.