Clean generated evidence/cache files without deleting source documents.
AI agents call cleanup_evidence_cache to permanently remove resources in Scifinder Route — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly removes (cleans up) generated evidence and cache files. While it explicitly preserves source documents, the deletion of cache/evidence files is not easily reversible. This qualifies as Destructive since data is permanently removed, even if only derived/cached data rather than primary source data.
From the tool's definition Clean generated evidence/cache files without deleting source documents
Attacks that exploit this kind of access
Clean generated evidence/cache files without deleting source documents. It is categorised as a Destructive tool in the Scifinder Route MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Scifinder Route MCP server in PolicyLayer and add a rule for cleanup_evidence_cache: 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 Scifinder Route. Nothing to install.
cleanup_evidence_cache 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_evidence_cache 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_evidence_cache. 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_evidence_cache is provided by the Scifinder Route MCP server (kettly1260/scifinder-route-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 →