Manually trigger a prune of remote media older than N days. The scheduled horizon job handles this on a recurring cadence; this lets operators force an aggressive pass. Rate-limited: 2/hour.
AI agents call pf_media_prune to permanently remove resources in Crow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Pruning remote media permanently removes files that cannot be recovered. The description explicitly frames this as a forceful, aggressive deletion operation beyond normal scheduled cleanup. Misuse could result in large-scale irreversible data loss across the platform.
From the tool's definition 'prune of remote media older than N days' and 'force an aggressive pass' — pruning media is irreversible deletion of stored content
Documented attack patterns abuse exactly the kind of access pf_media_prune gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for pf_media_prune:
{
"version": "1",
"default": "deny",
"hide": [
"pf_media_prune"
]
} pf_media_prune disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Manually trigger a prune of remote media older than N days. The scheduled horizon job handles this on a recurring cadence; this lets operators force an aggressive pass. Rate-limited: 2/hour. It is categorised as a Destructive tool in the Crow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Crow MCP server in PolicyLayer and add a rule for pf_media_prune: 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 Crow. Nothing to install.
pf_media_prune 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 pf_media_prune 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 pf_media_prune. 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.
pf_media_prune is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.