Purge Cloudflare
AI agents call purge_cache to permanently remove resources in Cloudflare MCP Server — 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: once cache entries are invalidated, they cannot be restored. This can cause significant performance degradation, increased origin load, and potential service disruption if misused at scale across zones. The server description also explicitly mentions 'cache purging' as a supported operation.
From the tool's definition Tool name 'purge_cache' and partial description 'Purge Cloudflare' — purging cache irreversibly removes cached content, requiring re-fetching from origin, and cannot be undone.
Attacks that exploit this kind of access
Purge Cloudflare. It is categorised as a Destructive tool in the Cloudflare MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cloudflare MCP Server MCP server in PolicyLayer and add a rule for 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 Cloudflare MCP Server. Nothing to install.
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 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 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.
purge_cache is provided by the Cloudflare MCP Server MCP server (ry-ops/cloudflare-mcp-server). 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 →