mcp-debugger: Instructions file for Claude Code

CLAUDE.md

mcp-debugger CLAUDE.md is an instructions file for Claude Code from debugmcp/mcp-debugger. It costs 11,787 tokens per session, scanned A, original, MIT.

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 for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is debugmcp/mcp-debugger's own configuration. It tells Claude Code how to work on mcp-debugger itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-debugger configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/ubuntu/.claude/local/claude.

Reuse

Borrowing it

Nothing to install: this file belongs to debugmcp/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/debugmcp/mcp-debugger/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/debugmcp/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.

agentmods badge for mcp-debugger CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/debugmcp/mcp-debugger/claude-md/github.svg)](https://agentmods.dev/instructions/debugmcp/mcp-debugger/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/debugmcp/mcp-debugger/claude-md"><img src="https://agentmods.dev/badge/instructions/debugmcp/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.

agentmods 80×15 button for mcp-debugger CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/debugmcp/mcp-debugger/claude-md"><img src="https://agentmods.dev/badge/instructions/debugmcp/mcp-debugger/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,787 This file is loaded in full into every session.
When invoked 11,787 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.11787 $0.11787
Opus 5.5 $0.04715 $0.04715
Sonnet 5.5 $0.02357 $0.02357
Haiku 4.5 $0.01179 $0.01179

Measured today against content hash 767fe62431aa, 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 today.

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 · 601 lines

How it starts

The opening of the file, as written. The whole thing — 601 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 + cobol)
│   ├── 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-cobol/      # COBOL debug adapter using GnuCOBOL + CodeLLDB behind a Node DAP shim
│   ├── adapter-dart/       # Dart/Flutter debug adapter using the SDK's own debug adapters behind a TCP-to-stdio bridge
│   ├── 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 the rust, cpp and cobol 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-cobol: COBOL debugging support via GnuCOBOL (cobc) + CodeLLDB behind a Node DAP shim that serves COBOL-shaped scopes/values from the compiler's dump metadata (launch + attach-by-PID)
  • @debugmcp/adapter-dart: Dart/Flutter debugging support via the SDK's own debug adapters (dart debug_adapter [--test], flutter debug-adapter [--test]) behind a TCP-to-stdio bridge; nothing vendored (launch + attach by VM-service URI)
  • @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 · 601 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. today Changed · +156 tokens per session 767fe62431aa
  2. 3d ago Changed · +36 tokens per session dbfa3b73540e
  3. 5d ago Changed · +201 tokens per session 704e49dbd712
  4. 12d ago Changed · +135 tokens per session bd612ceabb69
  5. 14d ago Changed · +74 tokens per session cff5eaaf3c7b
  6. 15d ago Changed · +12 lines · +1,077 tokens per session 3d208c2bae15
  7. 19d ago Changed · +1 lines · +188 tokens per session 3806a5b4e268
  8. 24d ago Changed · +1 lines · +106 tokens per session 50e48866a2c0
  9. 25d ago Changed · +67 tokens per session 936943aa3dad
  10. 26d ago First seen · 587 lines · 9,747 tokens per session scan A 81eb3c0a4d75

Subscribe to this mod's changes

mcp-debugger CLAUDE.md is an instructions file published in the GitHub repository debugmcp/mcp-debugger (180 stars, last pushed today), licensed MIT. It adds 11,787 tokens to every session, about $0.0471 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 2026-08-30.

Related

Other instructions, from other repositories

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 · 9,715 tokens

next.js AGENTS.md

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 · 7,581 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens