Health/identity probe — confirms the read token works and the dashboard is reachable.
AI agents call kpi_health to retrieve information from Wealify Kpi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple health check that verifies connectivity and token validity. It retrieves status information only, produces no side effects, and does not create, modify, delete, or execute any operations. It is clearly a Read operation with minimal blast radius — the only risk is information disclosure about system availability.
From the tool's definition Tool name is 'kpi_health' and description states 'Health/identity probe — confirms the read token works and the dashboard is reachable.' This is a diagnostic query that retrieves status information without modifying data.
Attacks that exploit this kind of access
Health/identity probe — confirms the read token works and the dashboard is reachable. It is categorised as a Read tool in the Wealify Kpi MCP Server, which means it retrieves data without modifying state.
Register the Wealify Kpi MCP server in PolicyLayer and add a rule for kpi_health: 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 Wealify Kpi. Nothing to install.
kpi_health 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 kpi_health 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 kpi_health. 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.
kpi_health is provided by the Wealify Kpi MCP server (ngkienmkqn/wealify-kpi-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 →