AI agents invoke lldb_run to trigger actions in LLDB-MCP. 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 triggers execution of native code with effects that depend on what program is loaded and its runtime behavior. While not inherently destructive, it can perform arbitrary operations (file I/O, network access, system calls) depending on the loaded program's logic.
From the tool's definition Tool name 'lldb_run' and description 'Run the loaded program' indicate execution of arbitrary native code. LLDB is a debugger that controls native application execution, and 'run' directly executes the loaded binary.
Documented attack patterns abuse exactly the kind of access lldb_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LLDB-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for lldb_run:
{
"version": "1",
"default": "deny",
"tools": {
"lldb_run": {
"limits": [
{
"counter": "lldb_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lldb_run 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.
Run the loaded program. It is categorised as a Execute tool in the LLDB-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LLDB- MCP server in PolicyLayer and add a rule for lldb_run: 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 LLDB-MCP. Nothing to install.
lldb_run 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_run 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_run. 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_run is provided by the LLDB- MCP server (stass/lldb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 LLDB-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
28 LLDB-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.