Skip to main content
Glama

Deepwiki MCP Server

by regenrek

Deepwiki MCP 服务器

这是一个非官方的 Deepwiki MCP 服务器

它通过 MCP 获取 Deepwiki URL,抓取所有相关页面,将其转换为 Markdown,然后返回一个文档或按页面列出的列表。

特征

  • 🔒域名安全:仅处理来自 deepwiki.com 的 URL
  • 🧹 HTML 清理:删除页眉、页脚、导航、脚本和广告
  • 🔗链接重写:调整链接以使其在 Markdown 中工作
  • 📄多种输出格式:获取一个文档或结构化页面
  • 🚀性能:快速爬行,并发性和深度可调
  • NLP :仅搜索库名称

用法

您可以使用的提示:

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

获取完整文档(默认)

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

单页

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

按简写获取

use deepwiki fetch tailwindlabs/tailwindcss
deepwiki fetch library deepwiki fetch url deepwiki fetch <name>/<repo> deepwiki multiple pages ... deepwiki single page url ...

光标

将其添加到.cursor/mcp.json文件。

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

Deepwiki 徽标

MCP 工具集成

该软件包注册了一个名为deepwiki_fetch的工具,您可以将其与任何兼容 MCP 的客户端一起使用:

{ "action": "deepwiki_fetch", "params": { "url": "https://deepwiki.com/user/repo", "mode": "aggregate", "maxDepth": "1" } }
参数
  • url (必填):Deepwiki 存储库的起始 URL
  • mode (可选):输出模式,对于单个 Markdown 文档为“aggregate”(默认),对于结构化页面数据为“pages”
  • maxDepth (可选):要抓取的页面的最大深度(默认值:10)

响应格式

成功响应(聚合模式)
{ "status": "ok", "data": "# Page Title\n\nPage content...\n\n---\n\n# Another Page\n\nMore content...", "totalPages": 5, "totalBytes": 25000, "elapsedMs": 1200 }
成功响应(页面模式)
{ "status": "ok", "data": [ { "path": "index", "markdown": "# Home Page\n\nWelcome to the repository." }, { "path": "section/page1", "markdown": "# First Page\n\nThis is the first page content." } ], "totalPages": 2, "totalBytes": 12000, "elapsedMs": 800 }
错误响应
{ "status": "error", "code": "DOMAIN_NOT_ALLOWED", "message": "Only deepwiki.com domains are allowed" }
部分成功响应
{ "status": "partial", "data": "# Page Title\n\nPage content...", "errors": [ { "url": "https://deepwiki.com/user/repo/page2", "reason": "HTTP error: 404" } ], "totalPages": 1, "totalBytes": 5000, "elapsedMs": 950 }

进度事件

使用该工具时,您将在抓取过程中收到进度事件:

Fetched https://deepwiki.com/user/repo: 12500 bytes in 450ms (status: 200) Fetched https://deepwiki.com/user/repo/page1: 8750 bytes in 320ms (status: 200) Fetched https://deepwiki.com/user/repo/page2: 6200 bytes in 280ms (status: 200)

本地开发 - 安装

本地使用

{ "mcpServers": { "mcp-deepwiki": { "command": "node", "args": ["./bin/cli.mjs"] } } }

来自源

# Clone the repository git clone https://github.com/regenrek/deepwiki-mcp.git cd deepwiki-mcp # Install dependencies npm install # Build the package npm run build
直接 API 调用

对于 HTTP 传输,您可以直接进行 API 调用:

curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -d '{ "id": "req-1", "action": "deepwiki_fetch", "params": { "url": "https://deepwiki.com/user/repo", "mode": "aggregate" } }'

配置

环境变量

  • DEEPWIKI_MAX_CONCURRENCY :最大并发请求数(默认值:5)
  • DEEPWIKI_REQUEST_TIMEOUT :请求超时(以毫秒为单位)(默认值:30000)
  • DEEPWIKI_MAX_RETRIES :失败请求的最大重试次数(默认值:3)
  • DEEPWIKI_RETRY_DELAY :重试退避的基本延迟(以毫秒为单位)(默认值:250)

要配置这些,请在项目根目录中创建一个.env文件:

DEEPWIKI_MAX_CONCURRENCY=10 DEEPWIKI_REQUEST_TIMEOUT=60000 DEEPWIKI_MAX_RETRIES=5 DEEPWIKI_RETRY_DELAY=500

Docker 部署(未经测试)

构建并运行 Docker 镜像:

# Build the image docker build -t mcp-deepwiki . # Run with stdio transport (for development) docker run -it --rm mcp-deepwiki # Run with HTTP transport (for production) docker run -d -p 3000:3000 mcp-deepwiki --http --port 3000 # Run with environment variables docker run -d -p 3000:3000 \ -e DEEPWIKI_MAX_CONCURRENCY=10 \ -e DEEPWIKI_REQUEST_TIMEOUT=60000 \ mcp-deepwiki --http --port 3000

发展

# Install dependencies pnpm install # Run in development mode with stdio pnpm run dev-stdio # Run tests pnpm test # Run linter pnpm run lint # Build the package pnpm run build

故障排除

常见问题

  1. 权限被拒绝:如果在运行 CLI 时出现 EACCES 错误,请确保使二进制文件可执行:
    chmod +x ./node_modules/.bin/mcp-deepwiki
  2. 连接被拒绝:确保端口可用且未被防火墙阻止:
    # Check if port is in use lsof -i :3000
  3. 超时错误:对于大型存储库,请考虑增加超时和并发性:
    DEEPWIKI_REQUEST_TIMEOUT=60000 DEEPWIKI_MAX_CONCURRENCY=10 npx mcp-deepwiki

贡献

欢迎大家贡献!详情请参阅CONTRIBUTING.md

执照

麻省理工学院

链接

课程

查看我的其他项目:

  • AI 提示- 为 Cursor AI、Cline、Windsurf 和 Github Copilot 精心策划的 AI 提示
  • codefetch - 使用一个简单的终端命令将代码转换为 LLM 的 Markdown
  • aidex一个 CLI 工具,提供有关 AI 语言模型的详细信息,帮助开发人员根据自己的需求选择正确的模型。# tool-starter
Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

MCP 服务器可获取 Deepwiki 文档并将其转换为 Markdown,从而允许用户从 deepwiki.com 存储库抓取页面并以不同的输出格式访问它们。

  1. 特征
    1. 用法
      1. 光标
        1. MCP 工具集成
        2. 响应格式
        3. 进度事件
      2. 本地开发 - 安装
        1. 本地使用
        2. 来自源
      3. 配置
        1. 环境变量
      4. Docker 部署(未经测试)
        1. 发展
          1. 故障排除
            1. 常见问题
          2. 贡献
            1. 执照
              1. 链接
                1. 课程
                  1. 查看我的其他项目:

                    Related MCP Servers

                    • A
                      security
                      A
                      license
                      A
                      quality
                      A powerful MCP server for fetching and transforming web content into various formats (HTML, JSON, Markdown, Plain Text) with ease.
                      Last updated -
                      4
                      146
                      12
                      TypeScript
                      MIT License
                      • Apple
                      • Linux
                    • -
                      security
                      F
                      license
                      -
                      quality
                      An MCP server that enables searching and retrieving content from Confluence documentation systems, providing capabilities for both document searches and full page content retrieval.
                      Last updated -
                      Python
                    • A
                      security
                      F
                      license
                      A
                      quality
                      A MCP server that allows you to search and retrieve content on any wiki site using MediaWiki with LLMs 🤖. wikipedia.org, fandom.com, wiki.gg and more sites using Mediawiki are supported!
                      Last updated -
                      2
                      8
                      Python
                    • -
                      security
                      F
                      license
                      -
                      quality
                      An MCP server that enables interaction with Markdown knowledge bases, allowing users to search and retrieve content by tags, text, URL, or date range from their local markdown files.
                      Last updated -
                      3
                      Python
                      • Apple

                    View all related MCP servers

                    MCP directory API

                    We provide all the information about MCP servers via our MCP API.

                    curl -X GET 'https://glama.ai/api/mcp/v1/servers/regenrek/deepwiki-mcp'

                    If you have feedback or need assistance with the MCP directory API, please join our Discord server