LldbSAFE
LLDB MCP server
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
See it in acton here, automatically debugging a buffer overflow: https://x.com/full_duplex/status/1904770477698277847
Overview
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:
- Starting and managing LLDB sessions
- Loading programs for debugging
- Setting breakpoints and watchpoints
- Controlling program execution
- Examining memory, registers, and variables
- Analyzing stack traces and program state
Features
- Create and manage multiple LLDB debugging sessions
- Load executables and attach to running processes
- Load core dump files for post-mortem analysis
- Execute arbitrary LLDB commands
- Fine-grained control over program execution
- Memory examination and disassembly
- Thread and stack frame inspection
Installation
- 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:
- Open the Claude desktop app configuration
- Add the following to your MCP configuration:
"mcpServers": {
"lldb-mcp": {
"command": "python3",
"args": ["/path/to/lldb-mcp/lldb_mcp.py"],
"disabled": false
}
}Usage
Once installed and configured, you can interact with LLDB through Claude using natural language.
Basic Workflow
- Start a new LLDB session
- Load a program
- Set breakpoints
- Run the program
- Inspect variables and memory
- Control execution (continue, step, next, etc.)
- Terminate the session when done
Example Commands
Here are some examples of how to interact with LLDB-MCP through Claude:
- "Start a new LLDB sessi
7646f773b6a7OBSERVED · 2026-10-07Exposed tools (28)
19 read · 6 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
lldb_attach | read | Attach to a running process |
lldb_backtrace | read | Show call stack |
lldb_breakpoint_delete | destructive | Delete a breakpoint |
lldb_breakpoint_list | read | List all breakpoints |
lldb_command | write | Execute an LLDB command |
lldb_continue | read | Continue program execution |
lldb_disassemble | read | Disassemble code |
lldb_examine | read | Examine memory |
lldb_expression | read | Evaluate an expression in the current frame |
lldb_finish | write | Execute until the current function returns |
lldb_frame_info | read | Get detailed information about a stack frame |
lldb_help | read | Get help for LLDB commands |
lldb_info_registers | read | Display registers |
lldb_kill | destructive | Kill the running process |
lldb_list_sessions | read | List all active LLDB sessions |
lldb_load | read | Load a program into LLDB |
lldb_load_core | read | Load a core dump file |
lldb_next | read | Step over function calls |
lldb_print | read | Print value of expression |
lldb_process_info | read | Get information about the current process |
lldb_run | write | Run the loaded program |
lldb_set_breakpoint | write | Set a breakpoint |
lldb_start | write | Start a new LLDB session |
lldb_step | read | Step program execution |
lldb_terminate | destructive | Terminate an LLDB session |
lldb_thread_list | read | List all threads in the current process |
lldb_thread_select | read | Select a specific thread |
lldb_watchpoint | write | Set a watchpoint on a variable or memory address |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
lldb_breakpoint_delete, lldb_kill, lldb_terminate
Gates applied: no_behavioural_pass.
7646f773b6a7full audit observations/trust-audit/mcp-server/stass__lldb.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 7646f773b6a7 | SAFE | B | 89 | first audit |
Questions
What is the Lldb MCP server?
LLDB MCP server
What tools does Lldb expose?
28 in total: 19 read-only, 6 that write, and 3 that can delete or overwrite (lldb_breakpoint_delete, lldb_kill, lldb_terminate). Every one is listed on this page with its risk.
Is Lldb safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Lldb need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (7646f773b6a7), read on 2026-10-07. The repository is watched and re-audited when it changes.