by stass
Integrates LLDB debugging capabilities with Claude's AI assistance, enabling natural‑language control of debugging sessions and streamlining AI‑assisted troubleshooting.
Lldb Mcp connects the LLDB debugger to Claude's Model Context Protocol, allowing users to start, manage, and interact with LLDB sessions through conversational commands.
mcp
(pip install mcp
).git clone https://github.com/stass/lldb-mcp.git
cd lldb-mcp
python3 lldb_mcp.py
mcpServers
configuration.Q: Which Python version is required? A: Python 3.7 or newer, plus a system‑installed LLDB.
Q: Can I use Lldb Mcp on Windows? A: LLDB support on Windows is limited; the tool works best on macOS and Linux where LLDB is fully functional.
Q: How do I enable detailed logging?
A: Start the server with the --debug
flag (python3 lldb_mcp.py --debug
).
Q: What if a command times out? A: Verify LLDB is correctly installed and reachable from the environment; also check permissions when attaching to processes.
Q: How are sessions identified? A: Each session receives a unique ID; include this ID in subsequent commands to target the correct debugging context.
See it in acton here, automatically debugging a buffer overflow: https://x.com/full_duplex/status/1904770477698277847
LLDB-MCP is a tool that integrates the LLDB debugger with Claude's Model Context Protocol (MCP). This integration allows Claude to start, control, and interact with LLDB debugging sessions directly, enabling AI-assisted debugging workflows.
The tool provides a comprehensive set of commands for working with LLDB, including:
Clone the repository:
git clone https://github.com/stass/lldb-mcp.git
cd lldb-mcp
Install dependencies:
pip install mcp
Configure Claude to use the LLDB-MCP server:
"mcpServers": {
"lldb-mcp": {
"command": "python3",
"args": ["/path/to/lldb-mcp/lldb_mcp.py"],
"disabled": false
}
}
Once installed and configured, you can interact with LLDB through Claude using natural language.
Here are some examples of how to interact with LLDB-MCP through Claude:
lldb_start
: Start a new LLDB sessionlldb_terminate
: Terminate an LLDB sessionlldb_list_sessions
: List all active LLDB sessionslldb_load
: Load a program into LLDBlldb_attach
: Attach to a running processlldb_load_core
: Load a core dump filelldb_run
: Run the loaded programlldb_continue
: Continue program executionlldb_step
: Step to next line or instructionlldb_next
: Step over function callslldb_finish
: Execute until the current function returnslldb_kill
: Kill the running processlldb_set_breakpoint
: Set a breakpointlldb_breakpoint_list
: List all breakpointslldb_breakpoint_delete
: Delete a breakpointlldb_watchpoint
: Set a watchpoint on a variable or memory addresslldb_backtrace
: Show call stacklldb_print
: Print value of expressionlldb_examine
: Examine memorylldb_info_registers
: Display registerslldb_frame_info
: Get detailed information about a stack framelldb_disassemble
: Disassemble codelldb_process_info
: Get information about the current processlldb_thread_list
: List all threads in the current processlldb_thread_select
: Select a specific threadlldb_command
: Execute an arbitrary LLDB commandlldb_expression
: Evaluate an expression in the current framelldb_help
: Get help for LLDB commandsexample/overflow.c
contains an example C program that causes buffer overflow with certain arguments.
Compile it using cc overflow.c
and ask Claude to debug the issue with the resulting program:
I'm trying to debug my program a.out that is crashing with certain arguments, e.g. when I pass "hello".
Can you help me debug it?
lldb_command
when you need to execute LLDB commands that don't have a dedicated function--debug
flag when starting the server for detailed loggingBSD 2-clause
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "lldb-mcp": { "command": "python3", "args": [ "/path/to/lldb-mcp/lldb_mcp.py" ], "env": {} } } }
Discover more MCP servers with similar functionality and use cases
by zed-industries
Provides real-time collaborative editing powered by Rust, enabling developers to edit code instantly across machines with a responsive, GPU-accelerated UI.
by cline
Provides autonomous coding assistance directly in the IDE, enabling file creation, editing, terminal command execution, browser interactions, and tool extension with user approval at each step.
by continuedev
Provides continuous AI assistance across IDEs, terminals, and CI pipelines, offering agents, chat, inline editing, and autocomplete to accelerate software development.
by github
Enables AI agents, assistants, and chatbots to interact with GitHub via natural‑language commands, providing read‑write access to repositories, issues, pull requests, workflows, security data and team activity.
by block
Automates engineering tasks by installing, executing, editing, and testing code using any large language model, providing end‑to‑end project building, debugging, workflow orchestration, and external API interaction.
by RooCodeInc
An autonomous coding agent that lives inside VS Code, capable of generating, refactoring, debugging code, managing files, running terminal commands, controlling a browser, and adapting its behavior through custom modes and instructions.
by lastmile-ai
A lightweight, composable framework for building AI agents using Model Context Protocol and simple workflow patterns.
by firebase
Provides a command‑line interface to manage, test, and deploy Firebase projects, covering hosting, databases, authentication, cloud functions, extensions, and CI/CD workflows.
by gptme
Empowers large language models to act as personal AI assistants directly inside the terminal, providing capabilities such as code execution, file manipulation, web browsing, vision, and interactive tool usage.