Fetch a list of KPIs for Wormhole from Wormholescan API.
AI agents call get_kpi_list to retrieve information from Wormhole Metrics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-computed KPI data from the Wormholescan API without modifying, executing operations, or affecting system state. It is a pure read operation querying existing analytics data about Wormhole protocol activity. The low severity reflects minimal blast radius—an AI could not harm systems or data through metric retrieval alone.
From the tool's definition Tool description states "Fetch a list of KPIs" which is a retrieval operation with no side effects. The server context confirms it 'analyzes' and 'provides insights' into metrics and KPIs.
Attacks that exploit this kind of access
Fetch a list of KPIs for Wormhole from Wormholescan API. It is categorised as a Read tool in the Wormhole Metrics MCP Server, which means it retrieves data without modifying state.
Register the Wormhole Metrics MCP server in PolicyLayer and add a rule for get_kpi_list: 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 Wormhole Metrics. Nothing to install.
get_kpi_list 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_kpi_list 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_kpi_list. 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_kpi_list is provided by the Wormhole Metrics MCP server (kukapay/wormhole-metrics-mcp). 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 →