AI agents call stats to retrieve information from Tages without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays statistics about memory usage patterns, access frequency, and session information. It performs no data modification, deletion, code execution, or financial operations. The activity is purely observational and read-only, making it the least risky category with minimal blast radius if misused by an agent.
From the tool's definition Tool name 'stats' and description 'Show memory usage statistics — counts by type, recall hit rate, agent sessions, most/least accessed' indicates retrieval and display of aggregate metrics and telemetry data with no modification or deletion of underlying data.
Attacks that exploit this kind of access
Show memory usage statistics — counts by type, recall hit rate, agent sessions, most/least accessed. It is categorised as a Read tool in the Tages MCP Server, which means it retrieves data without modifying state.
Register the Tages MCP server in PolicyLayer and add a rule for 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 Tages. Nothing to install.
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 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 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.
stats is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →