AI agents call get_cache_stats to retrieve information from Toonify without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries cache statistics without modifying, deleting, or executing any operations. It is purely informational, making it a Read category tool with low severity since exposing cache statistics has minimal security impact.
From the tool's definition Tool name 'get_cache_stats' and description 'Get detailed cache statistics (LRU cache + Prompt cache)' indicate read-only retrieval of cache metadata and statistics with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_cache_stats gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Toonify, and nothing reaches the server without passing your rules. This is the rule we recommend for get_cache_stats:
{
"version": "1",
"default": "deny",
"tools": {
"get_cache_stats": {}
}
}get_cache_stats is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get detailed cache statistics (LRU cache + Prompt cache). It is categorised as a Read tool in the Toonify MCP Server, which means it retrieves data without modifying state.
Register the Toonify MCP server in PolicyLayer and add a rule for get_cache_stats: 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 Toonify. Nothing to install.
get_cache_stats is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_cache_stats 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 get_cache_stats. 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.
get_cache_stats is provided by the Toonify MCP server (pcircle-ai/toonify-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Toonify tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Toonify tools catalogued and risk-classified — across an index of 42,500+ MCP servers.