Hard-delete terminal runs older than the cutoff, cascading to tasks, leases, attempts, snapshots, and events.
AI agents call prune_runs to permanently remove resources in State Trace — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of historical operational data. The use of 'hard-delete' and 'cascading' indicates data destruction that cannot be recovered. While scoped to 'terminal runs' and time-based cutoffs (which provide some guardrails), the blast radius includes complete removal of audit trails and task history. An agent misusing this could lose critical state and debugging information.
From the tool's definition "Hard-delete terminal runs older than the cutoff, cascading to tasks, leases, attempts, snapshots, and events." The tool irreversibly deletes data across multiple related entities (runs, tasks, leases, attempts, snapshots, events) with cascade semantics and…
Attacks that exploit this kind of access
Hard-delete terminal runs older than the cutoff, cascading to tasks, leases, attempts, snapshots, and events. It is categorised as a Destructive tool in the State Trace MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the State Trace MCP server in PolicyLayer and add a rule for prune_runs: 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 State Trace. Nothing to install.
prune_runs is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the prune_runs 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 prune_runs. 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.
prune_runs is provided by the State Trace MCP server (agent-pattern-labs/state-trace). 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 →