Clear all cached data to force fresh API requests
AI agents call clear_cache to permanently remove resources in Canvas MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing the cache permanently destroys stored data that cannot be recovered (it must be re-fetched). While the underlying source data is unaffected, the cached data itself is irreversibly deleted, fitting the Destructive category. Severity is medium because misuse causes performance degradation and forces re-fetching but does not affect canonical data.
From the tool's definition 'Clear all cached data' — irreversibly removes all cached data, forcing fresh API requests
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Clear all cached data to force fresh API requests. It is categorised as a Destructive tool in the Canvas MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Canvas MCP server in PolicyLayer and add a rule for clear_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 Canvas MCP. Nothing to install.
clear_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 clear_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 clear_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.
clear_cache is provided by the Canvas MCP server (noahjohannessen/canvas-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 →