How do I set breakpoints reliably?
Use full `file://` URLs when specifying the file path in the `set_breakpoint` tool, for example `file:///Users/you/project/script.js`.
@qckfx
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"debugger-mcp": {
"type": "stdio",
"command": "node",
"args": [
"build/index.js"
],
"env": {
"NODE_ENV": "production"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Node Debugger is an MCP server that provides Node.js debugging capabilities with process management for AI agents. It integrates with the Node.js Inspector API, allowing agents to start, stop, and debug Node.js processes using full Chrome DevTools Protocol.
Install by running npm install and npm run build, then configure the server with Claude Code via the .mcp.json file or by adding it to global configuration using claude mcp add. Once configured, agents can use tools like start_node_process, attach_debugger, set_breakpoint, step_debug, and evaluate_expression.
--inspect-brk flagUse full `file://` URLs when specifying the file path in the `set_breakpoint` tool, for example `file:///Users/you/project/script.js`.
The server launches Node.js scripts with the `--inspect-brk` flag, which pauses execution at the first line, allowing the debugger to connect before any code runs.
It uses the full Chrome DevTools Protocol, providing real debugging (not simulation) through the Node.js Inspector API.
It requires a Node.js environment to build and run the server itself. The managed processes also need Node.js to execute.
Use the `list_processes` tool to show all processes managed by the server, or access the `debug://processes` resource.
Painless E2E Automation for Mobile and Web

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Model Context Protocol Servers

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
🚀 The fast, Pythonic way to build MCP servers and clients.
评论