AI agents call agent_metrics 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 queries metrics about agent performance and memory system statistics. It performs no modifications, deletions, code execution, or financial operations. The verb 'Get' confirms read-only behavior. Even in the context of an AI agent, misusing this tool would only result in accessing performance telemetry data with no destructive or operational consequences.
From the tool's definition Tool name 'agent_metrics' and description 'Get agent effectiveness metrics — recall hit rate, memory creation quality, convention compliance' indicate pure data retrieval with no side effects.
Attacks that exploit this kind of access
Get agent effectiveness metrics — recall hit rate, memory creation quality, convention compliance. 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 agent_metrics: 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.
agent_metrics 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 agent_metrics 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 agent_metrics. 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.
agent_metrics 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 →