Manage the local DuckDB cache: remove or clear cached data.
AI agents call cache_manage to permanently remove resources in Ontario Data — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly removes or clears cached datasets from local storage. While the original source data on Ontario's open data portals remains intact, the local cache data is deleted and cannot be recovered without re-downloading. This qualifies as Destructive. Severity is medium because it only affects local cache (re-downloadable), not source data.
From the tool's definition 'remove or clear cached data' — explicitly deletes cached data from the local DuckDB cache
Attacks that exploit this kind of access
Manage the local DuckDB cache: remove or clear cached data. It is categorised as a Destructive tool in the Ontario Data MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ontario Data MCP server in PolicyLayer and add a rule for cache_manage: 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 Ontario Data. Nothing to install.
cache_manage 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 cache_manage 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 cache_manage. 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.
cache_manage is provided by the Ontario Data MCP server (sprine/ontario-data-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 →