LLDB_MCP
LLDB MCP implementation
claude mcp add --transport stdio ankur106-lldb_mcp node /path/to/LLDB_MCP/build/index.js
How to use
This MCP server exposes LLDB debugging capabilities as MCP commands that you can invoke from Claude or any MCP-enabled assistant. It allows you to start and manage LLDB sessions, load binaries and core dumps, set breakpoints, inspect memory, view registers and call stacks, and execute arbitrary LLDB commands through structured MCP messages. The server acts as a bridge between natural language or scripted intents and LLDB's debugging workflow, enabling interactive debugging within conversational contexts.
To use it, configure the MCP client (e.g., Claude) to point at the LLDB MCP server entry with the provided command and argument setup. Once connected, you can issue commands like lldb_start, lldb_load, lldb_command, lldb_backtrace, lldb_print, lldb_set_breakpoint, and lldb_continue to control debugging sessions and retrieve structured results suitable for chat-based responses. You can manage multiple sessions, attach to processes, and load core dumps as needed during a debugging session.
How to install
Prerequisites:
- Node.js and npm installed on your system
- Access to the repository (via git)
Installation steps:
-
Clone the repository: git clone git@github.com:ankur106/LLDB_MCP.git
-
Navigate to the project directory: cd LLDB_MCP
-
Install dependencies: npm install
-
Build the project: npm run build
-
Run the MCP server (example): node build/index.js
-
(Optional) Register the server in your MCP client configuration (as shown in the README) so clients can discover and connect to the lldb MCP server.
Additional notes
Tips and common issues:
- Ensure the build step completes successfully before running the server; missing build artifacts will cause startup failures.
- When configuring the MCP client, use a stable path to the built index.js to avoid mismatches after rebuilds.
- If you see permission or port issues, verify that the process has network access and the intended port is not blocked by a firewall.
- LLDB sessions may require appropriate permissions to attach to processes; run as a user with sufficient rights or adjust system security settings accordingly.
- For complex debugging workflows, consider creating macros or scripted sequences that combine multiple lldb_* commands into a single MCP invocation to streamline conversations.
Related MCP Servers
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
ironcurtain
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
CanvasMCPClient
Canvas MCP Client is an open-source, self-hostable dashboard application built around an infinite, zoomable, and pannable canvas. It provides a unified interface for interacting with multiple MCP (Model Context Protocol) servers through a flexible, widget-based system.
create -app
A CLI tool for quickly scaffolding Model Context Protocol (MCP) server applications with TypeScript support and modern development tooling
grok-faf
First MCP server for Grok | FAST⚡️AF • URL-based AI context • Vercel-deployed
mcp-turso
MCP server for interacting with Turso-hosted LibSQL databases