How does Lldb_mcp handle command execution?
Lldb_mcp calls `HandleCommand` with `SetAsync(False)` to block and capture all output directly. This avoids complex event listeners and polling.
Lldb MCP Server
@stableversion
Basic information
About Lldb MCP Server
A proper, clean LLDB MCP server with minimal dependencies and all functionality!
Lldb MCP Server config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryLldb MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Lldb_mcp?
Lldb_mcp is a simple MCP server for the LLDB debugger with minimal dependencies. It provides two commands (lldb_init and lldb) and works well with o4-mini and Gemini 2.5 Pro. Output is captured automatically, so no copy-paste is needed.
How to use Lldb_mcp?
Clone the repository, create a Python virtual environment, install fastmcp, then configure your MCP client with the path to the virtual environment’s Python and the lldb_mcp.py script. Additionally, import lldb_server.py into a running LLDB session. The server must be started manually inside an LLDB session.
Key features of Lldb_mcp
- Minimal dependencies (less than 200 lines of code)
- Only two commands:
lldb_initandlldb - Automatic output capture – no manual copy-paste
- Synchronous LLDB operation avoids complex event listeners
- Command chaining is disallowed for safety
- Returns “Executed successfully” when a command produces no output
Use cases of Lldb_mcp
- Debugging programs using LLMs that can issue LLDB commands
- Automating LLDB interactions via MCP protocol without manual terminal work
- Using o4-mini or Gemini 2.5 Pro to control LLDB debugging sessions
- Safe, manually‑started LLDB command execution with a blacklist of dangerous commands
Frequently asked questions
What are the runtime requirements for Lldb_mcp?
Python 3, the `fastmcp` library, and a running LLDB session. The server must be started manually inside an LLDB session.
Where does data live?
All LLDB commands are executed in the local LLDB session; no data is sent to external servers except what the MCP protocol exchanges with the client.
What are known limitations of Lldb_mcp?
Some commands may succeed without output (handled by returning “Executed successfully”). The “Continue” command can run indefinitely until a breakpoint is hit, causing the MCP to wait forever. o4-mini may hallucinate the `--address` flag in memory commands.
How does Lldb_mcp ensure safety?
The server must be started manually in a LLDB session. Certain commands are blacklisted (see `lldb_server.py`), and command chaining is not allowed.
More Other MCP servers
Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
88.2K
EverArt
modelcontextprotocolModel Context Protocol Servers
88.1K
Screenpipe
screenpipeYC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
22.0K
Yuppsy
Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Handl
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments