AI agents call lldb_help to retrieve information from LLDB-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves help documentation for LLDB commands, which is a read-only informational query. It does not execute code, modify state, attach to processes, set breakpoints, or perform any operations that alter the debugging environment or target application. The exposure is minimal since it only provides command reference information.
From the tool's definition Tool name is 'lldb_help' and description states 'Get help for LLDB commands' — a retrieval operation that queries and returns documentation/information about available commands with no side effects.
Documented attack patterns abuse exactly the kind of access lldb_help 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_help:
{
"version": "1",
"default": "deny",
"tools": {
"lldb_help": {}
}
}lldb_help is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get help for LLDB commands. It is categorised as a Read tool in the LLDB-MCP MCP Server, which means it retrieves data without modifying state.
Register the LLDB- MCP server in PolicyLayer and add a rule for lldb_help: 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_help is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the lldb_help 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_help. 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_help 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.