AI agents invoke lldb_expression 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.
Expression evaluation in LLDB is not merely a read operation; it can invoke functions, allocate memory, modify program state, or cause crashes. The blast radius is high because misuse could corrupt the debugged process or execute unintended logic.
From the tool's definition "Evaluate an expression in the current frame" — executing arbitrary expressions in a debugger context can run arbitrary code, call functions, modify memory, or trigger side effects in the attached process.
Documented attack patterns abuse exactly the kind of access lldb_expression 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_expression:
{
"version": "1",
"default": "deny",
"tools": {
"lldb_expression": {
"limits": [
{
"counter": "lldb_expression_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lldb_expression 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.
Evaluate an expression in the current frame. 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_expression: 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_expression 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_expression 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_expression. 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_expression 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.