mcp-nodejs-debugger
browser-tools-mcp
mcp-nodejs-debugger | browser-tools-mcp | |
---|---|---|
4 | 1 | |
278 | 6,348 | |
2.9% | 5.4% | |
6.6 | 8.7 | |
5 months ago | 5 months ago | |
JavaScript | JavaScript | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
mcp-nodejs-debugger
-
Show HN: We made an MCP server so Cursor can debug Node.js on its own
Up to you, but there's actually a formal logging pathway[1] in MCP that has the potential to put this message somewhere that either of the two consumers[2] of your service could see it https://github.com/hyperdrive-eng/mcp-nodejs-debugger/blob/v...
1: https://spec.modelcontextprotocol.io/specification/2024-11-0...
2: the person, and while I don't have evidence of it I also can't think why the LLM couldn't see the message, either
- Show HN: Let Claude Code control Node.js debugger
-
AI Blindspots – Blindspots in LLMs I've noticed while AI coding
Little tangent: I realized that currently LLMs can't debug because they only have access to the compile time (just code). Many bugs happen due to run time complex state. If I can make LLMs think like a productive Dev who can debug, then would they become more efficient?
I started hacking a small prototype along those lines: https://github.com/hyperdrive-eng/mcp-nodejs-debugger
Hoping I can avoid debug death loop where I get into this bad loop of copy pasting the error and hoping LLM would get it right this one time :)
browser-tools-mcp
-
Show HN: We made an MCP server so Cursor can debug Node.js on its own
Thanks for the detailed write-up, this is super useful! I really appreciate it.
> Claude captures all the NPM commands from the package json into the instructional file
Oh neat, I didn't know that. I'll try to use `/init` next time!
> it kept trying to run `npm run dev` which spins up the app itself. That's... not ideal since I'm running it myself so it can hot-reload
+1 I regularly notice that behaviour too. I'm running node in dev mode, then Cursor wants to run node, but the port is already in use.
> I'd be curious about is if there is a "clientside browser" MCP
Great point, I noticed this is a common feature request for front-end development. I haven't used it myself, but multiple people mentioned BrowserTools [1]. I think it can read the Dev Tools console, but I'm not sure about multimodal or access to the DOM.
[1]: https://github.com/AgentDeskAI/browser-tools-mcp
What are some alternatives?
context7 - Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
claude-task-master - An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
mcp-server-elasticsearch
puremd-mcp - Unblock, scrape, and search tools for MCP clients
mcp-server - A generic, modular server for implementing the Model Context Protocol (MCP).