Lldb MCP

🚀 LLDB-MCP

LLDB-MCP is a tool that integrates the LLDB debugger with Claude's Model Context Protocol (MCP), enabling AI-assisted debugging workflows.

🚀 Quick Start

LLDB-MCP is a tool integrating the LLDB debugger with Claude's Model Context Protocol (MCP). This integration allows Claude to directly initiate, control, and interact with LLDB debugging sessions, enabling an AI-assisted debugging workflow.

You can perform LLDB debugging through Claude's natural language after installation and configuration.

✨ Features

• Create and manage multiple LLDB debugging sessions.
• Load executable files and attach to running processes.
• Load core dump files for troubleshooting analysis.
• Execute arbitrary LLDB commands.
• Provide fine-grained control over program execution.
• Examine memory and perform decompilation.
• Inspect threads and stack frames.

📦 Installation

1. Clone the repository:

git clone https://github.com/stass/lldb-mcp.git
cd lldb-mcp

2. Install dependencies:

pip install mcp

3. Configure Claude to use the LLDB-MCP server:

• Open the Claude desktop application configuration.
• Add the following to your MCP configuration:

"mcpServers": {
  "lldb-mcp": {
    "command": "python3",
    "args": ["/path/to/lldb-mcp/lldb_mcp.py"],
    "disabled": false
  }
}

💻 Usage Examples

Basic Usage

After installation and configuration, you can use natural language in Claude to perform LLDB debugging.

Advanced Usage

• Use the --debug flag to start the server for detailed logs.
• Each session has a unique ID - ensure you use the correct ID when executing commands.
• Sessions are automatically cleaned up when the server is shut down.

📚 Documentation

Command List

• lldb_command: Use when you need to execute an LLDB command without a dedicated function.
• Refer to the Supported Commands section for other specific commands.

Requirements

• Python 3.7+
• LLDB installed on the system
• Claude desktop application with MCP support

Troubleshooting

• If an LLDB command times out, check if LLDB is installed correctly.
• Verify the path when starting a new session.
• Check for permission issues when attaching to a process.
• If a command does not execute correctly, view the debug logs.

⚠️ Important Note

Here you can view real-time automatic debugging of buffer overflows: https://x.com/full_duplex/status/1904770477698277847

💡 Usage Tip

Use the --debug flag to start the server for detailed logs. Each session has a unique ID, so make sure to use the correct ID when executing commands. Sessions will be automatically cleaned up when the server is shut down.