AI agents call lldb_list_sessions 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 information about active debugging sessions with no side effects. However, severity is elevated to 'medium' rather than 'low' because the information returned (active LLDB sessions) could reveal sensitive debugging contexts, attached processes, or memory analysis activities happening on the system, which an AI agent could exploit for reconnaissance or to identify vulnerable processes to attack.
From the tool's definition Tool name 'lldb_list_sessions' and description 'List all active LLDB sessions' indicate a query/retrieval operation that enumerates existing sessions without modifying them.
Documented attack patterns abuse exactly the kind of access lldb_list_sessions 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_list_sessions:
{
"version": "1",
"default": "deny",
"tools": {
"lldb_list_sessions": {}
}
}lldb_list_sessions 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.
List all active LLDB sessions. 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_list_sessions: 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_list_sessions 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_list_sessions 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_list_sessions. 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_list_sessions 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.