What is node-debugger-mcp CLAUDE.md?

Repository instructions for a Model Context Protocol server that lets AI agents debug Node.js programs. Debugging means pausing a running program, inspecting it, and evaluating code to find problems.

Building and running the Node.js debugger server, starting development watch mode, and inspecting the server with the MCP Inspector.

It gives agents the project’s build commands, architecture, and development conventions in one place. The server’s documented features include debug sessions, breakpoints, and code evaluation.

node-debugger-mcp CLAUDE.md — Instructions file by qckfx

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/qckfx/node-debugger-mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/qckfx/node-debugger-mcp

Per session 626 This file is loaded in full into every session.

When invoked 626 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00626	$0.00626
Opus 5	$0.00313	$0.00313
Sonnet 5	$0.00125	$0.00125
Haiku 4.5	$0.00063	$0.00063

Measured 2d ago against content hash 1b0df7197330, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

node-debugger-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Debugger MCP - a Model Context Protocol server that provides Node.js debugging capabilities for AI agents. It allows programmatic control of Node.js processes through debug sessions, breakpoints, and code evaluation.

Development Commands

npm run build - Compile TypeScript to build/ directory (required before first use)
npm run dev - Run TypeScript compiler in watch mode for development
npm start - Run the compiled MCP server
npm run inspector - Launch MCP inspector tool for debugging the server itself

Architecture

Core Structure

Single-file MCP server: src/index.ts contains the complete NodeDebuggerServer implementation
ES Modules: Project uses "type": "module" with ES2022 target
MCP Integration: Implements the Model Context Protocol for AI agent interaction

Key Components

NodeDebuggerServer class: Main server with process management and debug tools
ManagedProcess interface: Tracks spawned Node.js processes with debug ports
DebugSession interface: Maintains debugging session state

MCP Tools Provided

start_node_process - Launch Node.js scripts with --inspect-brk debugging (auto-pauses at start)
kill_process - Terminate managed processes
list_processes - Show all managed processes
attach_debugger - Connect to debug port
set_breakpoint - Set breakpoints with optional conditions
- IMPORTANT: Use full file:// URLs for reliable breakpoints (e.g., file:///absolute/path/to/file.js)
step_debug - Step through execution (next, step, continue, out)
pause_execution - Manually pause a running process
evaluate_expression - Evaluate expressions in debug context

MCP Resources

debug://session - Current debug session state
debug://processes - List of managed processes

Testing

Use example-app.js for testing debugging features:

npm run build
node --inspect=9229 example-app.js

Read the full file on GitHub · 63 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 63 lines · 626 tokens per session scan A 1b0df7197330

Subscribe to this mod's changes

node-debugger-mcp CLAUDE.md is an instructions file published in the GitHub repository qckfx/node-debugger-mcp (16 stars, last pushed 1y ago), licensed MIT. It adds 626 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Debugging

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

node-debugger-mcp CLAUDE.md