VS Code Debugger MCP Server
A bridge that enables AI assistants to connect to VS Code's debugger, allowing them to interact with and control debugging sessions through websocket connections.
README
VS Code Debugger MCP Server Proxy
This proxy acts as a bridge, enabling AI assistants that communicate via stdio to connect to the VS Code Debugger MCP Server, which uses HTTP or SSE.
Why Use This Proxy?
This tool is essential if your AI assistant does not support direct HTTP or SSE connections and requires a stdio-based server to interact with the VS Code debugger. It translates the stdio communication from your AI tool into a format the main debugger extension can understand.
Supercharge Your AI with the Main Extension
This proxy is a companion to the VS Code Debugger MCP Server extension. The main extension is what gives your AI its debugging superpowers.
Install it from the VS Code Marketplace
Prerequisites
Before you begin, ensure you have the following installed:
- Node.js and npm: Download and install Node.js.
- VS Code Debugger MCP Server: Install the main extension from the VS Code Marketplace.
Important: Extension Settings
To use this proxy, you must set the transport type of the VS Code Debugger MCP Server extension to "websocket" in the extension's settings in VS Code.
- Open VS Code.
- Go to Settings (
Ctrl+,). - Search for VSCode Debugger MCP Server.
- Set the Transport Type to
websocket.
Installation and Build
Follow these steps to get the proxy up and running:
-
Clone the repository:
git clone https://github.com/your-username/vscode-debugger-mcp-server-proxy.git cd vscode-debugger-mcp-server-proxy -
Install dependencies:
npm install -
Build the project:
npm run buildThis will compile the TypeScript source code into JavaScript in the
distdirectory.
Configuration
To connect your AI assistant, you need to configure it to use this proxy. Here is an example configuration for Roo Code:
Stdio MCP Server Config for Roo Code
Add the following to your Roo Code settings:
{
"mcpServers": {
"vscode-debugger": {
"command": "node",
"args": [
"d:/Projekte/MCP/vscode-debugger-mcp-server-proxy/dist/index.js",
"-p",
"10101"
],
"env": {
"DEBUG": "false"
},
"disabled": false,
"type": "stdio"
}
}
}
Important: Make sure the path in the args array is the absolute path to the compiled index.js file on your system.
Note: The port number (10101 in the example above) must match the port configured and Transport Type is set to websocket in the VS Code Debugger MCP Server extension settings. Ensure both the proxy and the extension are set to use the same port for successful communication.
How It Works
The proxy sits between your AI assistant and the main debugger extension, translating communication between them.
<p align="center"> <img src="docs/workflow.png" alt="Workflow Diagram" width="500"/> </p>
License
This project is open source and licensed under the MIT License.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。