AI agents call find_executions to retrieve information from Pernosco without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries execution trace data to locate function calls and inspect their state through expression evaluation. While it evaluates expressions, this is limited to read-only inspection of trace data within Pernosco's debugging context, not execution of arbitrary code with side effects in the user's system.
From the tool's definition Tool performs query operations: 'Find all calls to a function across the trace' and 'evaluate C++ expressions at each call site' are read-only inspection and analysis activities on a debugging trace database.
Attacks that exploit this kind of access
Find all calls to a function across the trace. Optionally evaluate C++ expressions at each call site using print_exprs (semicolon-delimited). It is categorised as a Read tool in the Pernosco MCP Server, which means it retrieves data without modifying state.
Register the Pernosco MCP server in PolicyLayer and add a rule for find_executions: 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 Pernosco. Nothing to install.
find_executions 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 find_executions 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 find_executions. 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.
find_executions is provided by the Pernosco MCP server (jnjaeschke/pernosco-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →