purge_cache_tool
AI agents call purge_cache_tool to permanently remove resources in MCP Cloudflare — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cache purging is an irreversible operation that permanently removes cached data, forcing re-fetching from origin. This can cause significant performance degradation and increased origin load if misused. The 'purge' verb strongly implies destructive/irreversible action. Confidence is reduced slightly because the description is empty, but the name is unambiguous.
From the tool's definition Tool name: purge_cache_tool — 'purge' indicates irreversible removal of cached content
Attacks that exploit this kind of access
purge_cache_tool. It is categorised as a Destructive tool in the MCP Cloudflare MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Cloudflare MCP server in PolicyLayer and add a rule for purge_cache_tool: 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 MCP Cloudflare. Nothing to install.
purge_cache_tool 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 purge_cache_tool 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 purge_cache_tool. 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.
purge_cache_tool is provided by the MCP Cloudflare MCP server (pypi:mcp-cloudflare-crunchtools). 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 →