Clear the CDN cache for an environment. Returns an operation_id.
AI agents invoke kinsta.cdn.clear-cache to trigger actions in Kinsta MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Clearing a CDN cache is an operational action that triggers an external infrastructure operation (invalidating cached content), causing cache misses and potential performance impact. It doesn't permanently delete data (content is re-cached from origin) but it does trigger an external operation with real effects, placing it in Execute.
From the tool's definition Clear the CDN cache for an environment
Attacks that exploit this kind of access
Clear the CDN cache for an environment. Returns an operation_id. It is categorised as a Execute tool in the Kinsta MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kinsta MCP Server MCP server in PolicyLayer and add a rule for kinsta.cdn.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 Kinsta MCP Server. Nothing to install.
kinsta.cdn.clear-cache is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the kinsta.cdn.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 kinsta.cdn.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.
kinsta.cdn.clear-cache is provided by the Kinsta MCP Server MCP server (jacob-hartmann/kinsta-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 →