AI agents call check_health to retrieve information from Cube Js MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only health check of the analytics server. It retrieves status information but does not execute queries, modify data, delete records, or trigger external operations. The health check is a standard monitoring operation with no destructive, financial, or execute-class capabilities. Blast radius is minimal—worst case, false health status could mislead monitoring, but no data is at risk.
From the tool's definition Tool name 'check_health' and description 'Checks the health status of the Cube.js server' indicate a query operation that retrieves server status information without modifying any data or triggering side effects.
Documented attack patterns abuse exactly the kind of access check_health gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cube Js MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for check_health:
{
"version": "1",
"default": "deny",
"tools": {
"check_health": {}
}
}check_health is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Checks the health status of the Cube.js server. It is categorised as a Read tool in the Cube Js MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cube Js MCP Server MCP server in PolicyLayer and add a rule for check_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 Cube Js MCP Server. Nothing to install.
check_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 check_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 check_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.
check_health is provided by the Cube Js MCP Server MCP server (zsembek/cube.js-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cube Js MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Cube Js MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.