What is mcp-debugger CLAUDE.md?

Project instructions for MCP Debugger, a Claude Code plugin that connects to real debuggers through the Debug Adapter Protocol. It documents the project structure, build commands, tests, and debugging support for Python, JavaScript or TypeScript, Go, and Rust.

Use it when working on MCP Debugger, including its server, debug-session manager, protocol client, build process, and test commands.

It gives a coding agent the repository-specific context needed to build, test, and modify the plugin consistently.

How bherbruck/mcp-debugger configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bherbruck/mcp-debugger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bherbruck/mcp-debugger/main/CLAUDE.md

Clone the repo

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

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bherbruck/mcp-debugger/claude-md/github.svg)](https://agentmods.dev/instructions/bherbruck/mcp-debugger/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bherbruck/mcp-debugger/claude-md"><img src="https://agentmods.dev/badge/instructions/bherbruck/mcp-debugger/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bherbruck/mcp-debugger/claude-md"><img src="https://agentmods.dev/badge/instructions/bherbruck/mcp-debugger/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 631 This file is loaded in full into every session.

When invoked 631 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00631	$0.00631
Opus 5.5	$0.00252	$0.00252
Sonnet 5.5	$0.00126	$0.00126
Haiku 4.5	$0.00063	$0.00063

Measured 2mo ago against content hash 473561017fea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-debugger 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 2mo 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

MCP Debugger is a multi-language debugging plugin for Claude Code that leverages the Debug Adapter Protocol (DAP) to provide real debugging capabilities across Python, JavaScript/TypeScript, Go, and Rust. It enables setting breakpoints, stepping through execution, inspecting variables, and evaluating expressions in real debuggers (debugpy, vscode-js-debug, Delve, CodeLLDB).

Build Commands

npm run build      # Compile TypeScript to bin/
npm run dev        # Watch mode for development
npm test           # Run vitest
npm run test:run   # Run tests once (CI mode)
npm start          # Run the compiled MCP server
npm run clean      # Remove bin/ directory

Architecture

Layer Structure

MCP Server (src/server.ts) - Routes tool calls from Claude Code to handlers, exposes 18+ debugging tools
Session Manager (src/session/session-manager.ts) - Central orchestrator managing debug session lifecycle and state
DAP Client (src/dap/dap-client.ts) - Implements Debug Adapter Protocol, handles message parsing and adapter processes
Adapters (src/adapters/) - Language-specific implementations for each debugger

Session State Machine

CREATED → INITIALIZING → READY → RUNNING ↔ PAUSED → TERMINATED (or ERROR)

Key Design Patterns

Adapter Pattern: Each language has an IDebugAdapter that handles installation, configuration, and launch for its debugger
Registry Pattern: AdapterRegistry maps languages to adapter factories
Event-Driven: EventEmitter used throughout; events bubble from DAP → Session Manager → MCP Server → Claude Code

Important Implementation Details

Multi-Session DAP: vscode-js-debug uses reverse requests for child sessions connecting via TCP
Async Launch: debugpy responds to launch only after configurationDone() - use launchAsync() and waitForLaunch()
Message Framing: DAP uses Content-Length headers with proper UTF-8 byte counting in message-parser.ts
Breakpoint Queueing: Breakpoints set before debugging starts are stored and applied once adapter is ready

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.

2mo ago First seen · 63 lines · 631 tokens per session scan A 473561017fea

Subscribe to this mod's changes

mcp-debugger CLAUDE.md is an instructions file published in the GitHub repository bherbruck/mcp-debugger (2 stars, last pushed 7mo ago), licensed MIT. It adds 631 tokens to every session, about $0.0025 per session on Opus 5.5. 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 2026-08-31.

Debugging

mcp-debugger CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-debugger CLAUDE.mdbherbruck/mcp-debugger	Instructions file	2	7mo ago	MIT	A	631	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-debugger: Instructions file for Claude Code