DeepWiki OMNeT++ MCP Server

DeepWiki OMNeT++ MCP Server

Enables querying OMNeT++ and INET Framework documentation from DeepWiki across multiple repositories, providing comprehensive answers about simulation framework development.

Category
访问服务器

README

DeepWiki OMNeT++ MCP Server

A custom MCP (Model Context Protocol) server that queries multiple repositories on DeepWiki, providing comprehensive answers about OMNeT++ and INET Framework development.

✨ Features

This MCP server provides three powerful tools for OMNeT++ and INET documentation:

  1. omnetpp_ask_question - Ask natural language questions about OMNeT++ and INET

    • Searches across multiple repositories simultaneously
    • Returns merged results with clear source attribution
  2. omnetpp_read_wiki_structure - Retrieve the complete documentation structure

    • Gets wiki topics from all configured repositories
  3. omnetpp_read_wiki_contents - Fetch detailed contents for specific topics

    • Queries all repositories for comprehensive coverage

🎯 Multi-Repository Support

The server now queries both repositories in parallel:

  • omnetpp/omnetpp - OMNeT++ simulation framework
  • inet-framework/inet - INET Framework for network simulations

Results are merged with clear headers showing which repository provided each answer. See MULTI_REPO_SETUP.md for details.

Installation

  1. Install dependencies:
npm install
  1. Build the project:
npm run build

The compiled server will be in the dist/ directory.

Configuration

Configure the MCP server based on your IDE/client:

For Cline (VS Code Extension) ⭐ RECOMMENDED

  1. Open VS Code Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows/Linux)

  2. Type "Preferences: Open User Settings (JSON)"

  3. Or directly edit:

    • macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
    • Windows: %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
    • Linux: ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
  4. Add this configuration (replace the path with your actual project location):

{
  "mcpServers": {
    "deepwiki-omnetpp": {
      "command": "node",
      "args": [
        "/absolute/path/to/MCP4omnetpp/dist/index.js"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}
  1. Reload VS Code: Cmd+Shift+P → "Developer: Reload Window"

For Windsurf IDE

  1. Open Windsurf settings

  2. Navigate to MCP Servers configuration

  3. Add a new server with:

    • Name: deepwiki-omnetpp
    • Command: node
    • Args: ["/absolute/path/to/MCP4omnetpp/dist/index.js"]
  4. Restart Windsurf

For Claude Desktop

macOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json Windows: Edit %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "deepwiki-omnetpp": {
      "command": "node",
      "args": [
        "/absolute/path/to/MCP4omnetpp/dist/index.js"
      ]
    }
  }
}

Restart Claude Desktop after saving.

For Cursor IDE

  1. Open Cursor Settings
  2. Navigate to Extensions → MCP Configuration
  3. Add the server configuration:
{
  "deepwiki-omnetpp": {
    "command": "node",
    "args": ["/absolute/path/to/MCP4omnetpp/dist/index.js"]
  }
}
  1. Restart Cursor

For Zed Editor

Edit your Zed configuration file and add:

{
  "context_servers": {
    "deepwiki-omnetpp": {
      "command": "node",
      "args": ["/absolute/path/to/MCP4omnetpp/dist/index.js"]
    }
  }
}

Important Notes

  • Replace /absolute/path/to/MCP4omnetpp/ with the actual absolute path to your project
  • On Windows, use double backslashes: C:\\Users\\YourName\\MCP4omnetpp\\dist\\index.js
  • Ensure Node.js is installed and accessible in your PATH
  • After configuration changes, always restart/reload your IDE/client

Verifying Installation

After reloading, check that the tools are available:

  1. Look for these tools in your MCP client:

    • omnetpp_ask_question
    • omnetpp_read_wiki_structure
    • omnetpp_read_wiki_contents
  2. Test with a simple query:

    Use tool: omnetpp_read_wiki_structure
    

Usage

Once configured, you'll have access to these tools in your MCP client:

Ask a Question

Use tool: omnetpp_ask_question
Parameters: { "question": "How do I create a simple network in OMNeT++?" }

Get Wiki Structure

Use tool: omnetpp_read_wiki_structure
Parameters: {}

Read Wiki Contents

Use tool: omnetpp_read_wiki_contents
Parameters: { "topic": "getting-started" }

How It Works

This server acts as an intelligent proxy with multi-repository support:

  1. Receives tool calls from MCP clients (Claude, Cline, Windsurf, etc.)
  2. Queries multiple repositories in parallel:
    • omnetpp/omnetpp (OMNeT++ core framework)
    • inet-framework/inet (INET network simulation)
  3. Connects to DeepWiki API via Streamable HTTP transport
  4. Merges results from all repositories with clear attribution
  5. Returns comprehensive answers combining insights from both sources

Architecture

┌─────────────┐         ┌──────────────────┐         ┌─────────────────┐
│  MCP Client │ stdio   │  This MCP Proxy  │  HTTP   │  DeepWiki API   │
│ (Cline/etc) │────────▶│  (Multi-Repo)    │────────▶│  (Public)       │
└─────────────┘         └──────────────────┘         └─────────────────┘
                               │
                               ├─▶ Query: omnetpp/omnetpp
                               └─▶ Query: inet-framework/inet
                                      (Parallel)

Benefits

✅ No manual repository specification - Automatically queries relevant repos
✅ Comprehensive answers - Get information from both OMNeT++ and INET
✅ Fast parallel queries - All repositories queried simultaneously
✅ Fault tolerant - One repo failing doesn't break the entire query
✅ Clear source attribution - Know which repo provided each answer

See MULTI_REPO_SETUP.md for more details on adding repositories.

Development

  • Source: src/index.ts
  • Build: npm run build
  • Output: dist/index.js

Technical Details

  • Built with the official @modelcontextprotocol/sdk (v1.25.3)
  • Uses JSON Schema for tool definitions (compatible with all MCP clients)
  • Uses Streamable HTTP transport to connect to DeepWiki
  • Proxies requests to https://mcp.deepwiki.com/mcp
  • Multi-repository querying: Queries multiple repos in parallel using Promise.allSettled()
  • Current repositories: omnetpp/omnetpp and inet-framework/inet
  • Fault tolerant: Failed queries don't break the entire response
  • Result merging: Combines answers with clear repository headers
  • Note: SSE transport was deprecated by DeepWiki in January 2026

Adding More Repositories

Edit src/index.ts and modify the REPOS array:

const REPOS = [
  "omnetpp/omnetpp",
  "inet-framework/inet",
  "your-org/your-repo"  // Add more here
];

Then rebuild with npm run build and reload your MCP client.

Troubleshooting

Server Not Starting

  • Ensure Node.js is installed and accessible
  • Check that the path in the configuration points to the correct dist/index.js file
  • Verify the build completed successfully

No Tools Available

  • Restart your MCP client (Claude Desktop or VSCode with Cline)
  • Check the MCP client logs for connection errors

API Errors

  • The DeepWiki API must be accessible
  • Check your internet connection
  • Verify the official DeepWiki MCP service is operational

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选