AI agents invoke lldb_start to trigger actions in GDB MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool starts a new LLDB (Low-Level Debugger) session, which launches a debugger capable of executing arbitrary binaries and running code. While primarily intended for debugging, an AI agent misusing this could execute malicious binaries, attach to sensitive processes, or inspect/modify running program state.
From the tool's definition Tool name: 'lldb_start' described as 'Start a new LLDB debugging session.' LLDB is a debugger that executes and controls program execution.
Documented attack patterns abuse exactly the kind of access lldb_start gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GDB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for lldb_start:
{
"version": "1",
"default": "deny",
"tools": {
"lldb_start": {
"limits": [
{
"counter": "lldb_start_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lldb_start stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Start a new LLDB debugging session. It is categorised as a Execute tool in the GDB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GDB MCP Server MCP server in PolicyLayer and add a rule for lldb_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches GDB MCP Server. Nothing to install.
lldb_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the lldb_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for lldb_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
lldb_start is provided by the GDB MCP Server MCP server (smadi0x86/mdb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 GDB MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 GDB MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.