Get email metrics with time-series aggregation.
AI agents call keyid_get_metrics to retrieve information from KeyID Agent Kit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves aggregated email metrics and statistics without modifying, deleting, or executing any operations. It is purely informational and poses minimal risk even if misused by an AI agent, as it only exposes already-owned metrics data.
From the tool's definition Tool name 'keyid_get_metrics' and description 'Get email metrics with time-series aggregation' indicate data retrieval only. The verb 'get' and absence of any modification, deletion, or execution language confirm read-only behavior.
Attacks that exploit this kind of access
Get email metrics with time-series aggregation. It is categorised as a Read tool in the KeyID Agent Kit MCP Server, which means it retrieves data without modifying state.
Register the KeyID Agent Kit MCP server in PolicyLayer and add a rule for keyid_get_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 KeyID Agent Kit. Nothing to install.
keyid_get_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 keyid_get_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 keyid_get_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.
keyid_get_metrics is provided by the KeyID Agent Kit MCP server (keyid-ai/agent-kit). 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 →