What is claude_lldb_mcp CLAUDE.md?

Repository instructions for an MCP server that gives Claude Code and other clients structured LLDB debugging tools. LLDB is a debugger for programs such as those written in C or C++.

It is for understanding the command-execution layer, input validation models, response formats, and the server's 17 debugging tools.

It explains how the server is organized and how it runs debugger commands, so contributors can work on it without guessing about the architecture or execution model.

How benpm/claude_lldb_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to benpm/claude_lldb_mcp. 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/benpm/claude_lldb_mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/benpm/claude_lldb_mcp

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/benpm/claude_lldb_mcp/claude-md.svg)](https://agentmods.dev/instructions/benpm/claude_lldb_mcp/claude-md)

Your own site

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

Per session 1,054 This file is loaded in full into every session.

When invoked 1,054 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	$0.01054	$0.01054
Opus 5	$0.00527	$0.00527
Sonnet 5	$0.00211	$0.00211
Haiku 4.5	$0.00105	$0.00105

Measured 7d ago against content hash e3227eab939e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude_lldb_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 7d 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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 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.

Overview

This is an MCP (Model Context Protocol) server that provides structured debugging tools for LLDB. It exposes 17 specialized tools for debugging C/C++ programs, designed for use with Claude Code and other MCP clients.

Architecture

Core Components

lldb_mcp_server.py - Single-file MCP server implementation with three main sections:

LLDB Command Execution Layer (lines 65-166)
- _run_lldb_command(): Execute single LLDB commands via subprocess
- _run_lldb_script(): Execute multiple LLDB commands in batch mode
- All LLDB interaction happens via command-line invocation, NOT Python bindings
- Commands run in batch mode with --batch and -o flags
Input Models (lines 179-583)
- Pydantic models for each tool's parameters
- All models use ConfigDict(str_strip_whitespace=True)
- Field validation with min/max lengths and ranges
- ResponseFormat enum for markdown vs JSON output
MCP Tools (lines 636-1451)
- 17 @mcp.tool() decorated async functions
- Each tool builds a command list, executes via _run_lldb_script(), and formats output
- Tools annotated with hints (readOnlyHint, destructiveHint, etc.)

Server Execution Model

Uses FastMCP from mcp.server.fastmcp
Runs in stdio mode for Claude Code integration
All LLDB commands run via subprocess (batch mode), no persistent debug sessions
Entry point: mcp.run() at line 1458

Global State

Lines 43-63 define DebugSession class and session storage (_sessions), but these are currently unused. The server is stateless - each tool invocation spawns a new LLDB process.

Common Development Commands

Running the Server

# Direct execution (for Claude Code)
python lldb_mcp_server.py

# With uvx
uvx --from . lldb-mcp

# Testing
python test_server.py

Testing and Validation

# Run test suite
pytest tests/

# Type checking
mypy lldb_mcp_server.py

# Linting
ruff check lldb_mcp_server.py

# Format code
ruff format lldb_mcp_server.py

Read the full file on GitHub · 142 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.

7d ago First seen · 142 lines · 1,054 tokens per session scan A e3227eab939e

Subscribe to this mod's changes

claude_lldb_mcp CLAUDE.md is an instructions file published in the GitHub repository benpm/claude_lldb_mcp (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,054 tokens to every session, about $0.0053 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 2026-08-31.

Building agents Debugging

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 · 5,153 tokens

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

claude_lldb_mcp: Instructions file for Claude Code