Clean up old, unused contexts that have expired
AI agents call prune_expired_contexts to permanently remove resources in Semantic Context MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Pruning expired contexts irreversibly deletes stored conversation contexts. Even though it targets 'expired' data, this is a destructive operation that cannot be undone. High severity because it could remove valuable context data if expiry logic is misconfigured or if an AI agent triggers it prematurely.
From the tool's definition 'Clean up old, unused contexts that have expired' — permanently removes/deletes stored context data
Attacks that exploit this kind of access
Clean up old, unused contexts that have expired. It is categorised as a Destructive tool in the Semantic Context MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Semantic Context MCP server in PolicyLayer and add a rule for prune_expired_contexts: 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 Semantic Context MCP. Nothing to install.
prune_expired_contexts 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_expired_contexts 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_expired_contexts. 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_expired_contexts is provided by the Semantic Context MCP server (semanticintent/semantic-wake-intelligence-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 →