Prune old proposal metadata, secret payloads, and snapshots from local state.
AI agents call cleanup_state to permanently remove resources in Safe Migrations — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes/prunes stored data (proposal metadata, secret payloads, snapshots) from local state. 'Prune' implies irreversible removal of records that cannot be recovered once deleted.
From the tool's definition Prune old proposal metadata, secret payloads, and snapshots from local state
Attacks that exploit this kind of access
Prune old proposal metadata, secret payloads, and snapshots from local state. It is categorised as a Destructive tool in the Safe Migrations MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Safe Migrations MCP server in PolicyLayer and add a rule for cleanup_state: 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 Safe Migrations. Nothing to install.
cleanup_state 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 cleanup_state 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 cleanup_state. 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.
cleanup_state is provided by the Safe Migrations MCP server (possibly6/safe-migrations-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 →