lisa.py
This project integrates LLDB with MCP, allowing AI assistants to interact with debugging sessions using natural language. It features a server and a plugin that facilitate a structured communication between the assistant and the debugger, enhancing debugging capabilities.
Overview
This project provides a Model-Context Protocol (MCP) integration for LLDB, enabling AI assistants like Claude to interact with debugging sessions. It consists of a server that communicates with Claude and a plugin that runs inside LLDB. Key features include creating debug targets, launching processes, attaching to processes, setting breakpoints, and more. Installation requires Python 3.10+, LLDB with Python bindings, the fastmcp package, and involves configuration via Claude for Desktop or direct LLDB integration.