AI agents call lldb_kill to permanently remove resources in LLDB-MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Killing a process is an irreversible destructive action: any unsaved state, in-flight operations, or data held by the process is permanently lost. This goes beyond a simple write or execute action and qualifies as Destructive due to the irreversible termination of the target process.
From the tool's definition 'Kill the running process' — terminates a process irreversibly, which cannot be undone
Documented attack patterns abuse exactly the kind of access lldb_kill 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_kill:
{
"version": "1",
"default": "deny",
"hide": [
"lldb_kill"
]
}lldb_kill disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Kill the running process. It is categorised as a Destructive tool in the LLDB-MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LLDB- MCP server in PolicyLayer and add a rule for lldb_kill: 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_kill is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the lldb_kill 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_kill. 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_kill 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.