mcp-debugger CLAUDE.md

Repository instructions for mcp-debugger, a server that lets AI agents debug programs step by step through structured tool calls. It explains the project's monorepo, meaning one repository containing several related packages, and its language-specific adapters.

In plain words
What is it for?
Use it when developing, debugging, or reviewing mcp-debugger and its Python, Ruby, JavaScript, Rust, Go, Java, or .NET adapter packages.
Why use it?
It gives an agent the project layout, package roles, and important commands needed to work in the repository without guessing.

Instructions file

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/debugmcp/mcp-debugger/claude-md
Clone the repo
git clone --depth 1 https://github.com/debugmcp/mcp-debugger
Per session 8,334 This file is loaded in full into every session.
When invoked 8,334 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.

ModelPer sessionOnce invoked
Fable 5 $0.08334 $0.08334
Opus 5 $0.04167 $0.04167
Sonnet 5 $0.01667 $0.01667
Haiku 4.5 $0.00833 $0.00833

Measured 2d ago against content hash 0815c2764c50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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 · 574 lines

How it starts

The opening of the file, as written. The whole thing — 574 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 Model Context Protocol (MCP) server that provides step-through debugging capabilities for AI agents. It acts as a bridge between MCP clients (like Claude) and debug adapters, enabling structured debugging operations through JSON-based tool calls.

The project uses a monorepo architecture with dynamic adapter loading, allowing language-specific debug adapters to be developed and deployed independently.

Monorepo Structure

mcp-debugger/
├── packages/
│   ├── shared/             # Shared interfaces, types, and utilities
│   ├── codelldb-common/    # Shared CodeLLDB vendoring/resolution (rust + cpp)
│   ├── adapter-python/     # Python debug adapter using debugpy
│   ├── adapter-ruby/       # Ruby debug adapter using rdbg (debug gem)
│   ├── adapter-javascript/ # JavaScript/Node.js adapter using js-debug
│   ├── adapter-rust/       # Rust debug adapter using CodeLLDB
│   ├── adapter-go/         # Go debug adapter using Delve
│   ├── adapter-java/       # Java debug adapter using JDI bridge
│   ├── adapter-dotnet/     # .NET/C# debug adapter using netcoredbg
│   ├── adapter-cpp/        # C/C++ debug adapter using CodeLLDB
│   ├── adapter-mock/       # Mock adapter for testing
│   └── mcp-debugger/       # Self-contained CLI bundle (npx distribution)
├── src/
│   ├── adapters/          # Adapter loading and registry system
│   ├── container/         # Dependency injection container
│   ├── proxy/             # DAP proxy system
│   └── session/           # Session management
└── tests/                 # Comprehensive test suite

Package Details

  • @debugmcp/shared: Core interfaces and types used across all packages
  • @debugmcp/codelldb-common: Shared CodeLLDB vendoring, resolver, and spawn glue (used by rust and cpp adapters)
  • @debugmcp/adapter-python: Python debugging support via debugpy
  • @debugmcp/adapter-ruby: Ruby debugging support via rdbg (debug gem)
  • @debugmcp/adapter-javascript: JavaScript/Node.js debugging support via js-debug
  • @debugmcp/adapter-rust: Rust debugging support via CodeLLDB
  • @debugmcp/adapter-go: Go debugging support via Delve
  • @debugmcp/adapter-java: Java debugging support via JDI bridge
  • @debugmcp/adapter-dotnet: .NET/C# debugging support via netcoredbg
  • @debugmcp/adapter-cpp: C/C++ debugging support via CodeLLDB (launch + attach-by-PID)
  • @debugmcp/adapter-mock: Mock adapter for testing and development
  • @debugmcp/mcp-debugger: Self-contained CLI bundle for npm distribution (npx-ready)

Read the full file on GitHub · 574 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.

  1. 2d ago First seen · 574 lines · 8,334 tokens per session scan A 0815c2764c50

Subscribe to this mod's changes

mcp-debugger CLAUDE.md is an instructions file published in the GitHub repository debugmcp/mcp-debugger (159 stars, last pushed 2d ago), licensed MIT. It adds 8,334 tokens to every session, about $0.0417 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens