cloudflare_purge_cache
AI agents call cloudflare_purge_cache to permanently remove resources in Integrations MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cache purging destroys existing cached content state and cannot be undone—the cache must be rebuilt from origin servers. While not data deletion per se, purging cache is functionally destructive as it irreversibly discards the current cache state. The high severity reflects potential business impact (CDN performance degradation, increased origin load, latency spikes).
From the tool's definition Tool name 'cloudflare_purge_cache' indicates irreversible cache clearing. 'Purge' is a destructive action that removes cached data without recoverability.
Attacks that exploit this kind of access
cloudflare_purge_cache. It is categorised as a Destructive tool in the Integrations MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Integrations MCP server in PolicyLayer and add a rule for cloudflare_purge_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 Integrations MCP. Nothing to install.
cloudflare_purge_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 cloudflare_purge_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 cloudflare_purge_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.
cloudflare_purge_cache is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →