AI agents call lldb_examine 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.
The tool reads/inspects memory contents of a running process. This is a read operation with no side effects on its own. However, it can expose sensitive data (secrets, keys, private data) from arbitrary memory addresses, giving it medium severity.
From the tool's definition Examine memory
Documented attack patterns abuse exactly the kind of access lldb_examine 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_examine:
{
"version": "1",
"default": "deny",
"tools": {
"lldb_examine": {}
}
}lldb_examine 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.
Examine memory. 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_examine: 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_examine 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_examine 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_examine. 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_examine 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.