get_metric
AI agents call get_metric to retrieve information from Klaviyo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix is a strong indicator of a read-only retrieval operation. In the context of a marketing automation platform like Klaviyo, metrics typically represent performance data (e.g., campaign opens, clicks, conversions). Retrieving such data has no side effects and poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'get_metric' suggests retrieval of metric data. Description is empty, limiting direct evidence, but the pattern of sibling tools (create_*, add_*, delete_*) and the tool's naming convention indicates it queries or retrieves existing metric…
Attacks that exploit this kind of access
get_metric. It is categorised as a Read tool in the Klaviyo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Klaviyo MCP Server MCP server in PolicyLayer and add a rule for get_metric: 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 Klaviyo MCP Server. Nothing to install.
get_metric 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_metric 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_metric. 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_metric is provided by the Klaviyo MCP Server MCP server (ivan-rivera-projects/klaviyo-mcp-server-enhanced). 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 →