query_prometheus_basic_info
AI agents call query_prometheus_basic_info to retrieve information from OpenShift OVN-Kubernetes Benchmark MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates querying Prometheus for basic information, a monitoring system. Querying metrics is a read-only operation with no side effects. Prometheus queries retrieve existing monitoring data without modification or execution.
From the tool's definition Tool name 'query_prometheus_basic_info' contains the verb 'query' which retrieves data. The prefix 'query_' indicates a data retrieval operation.
Attacks that exploit this kind of access
query_prometheus_basic_info. It is categorised as a Read tool in the OpenShift OVN-Kubernetes Benchmark MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenShift OVN-Kubernetes Benchmark MCP Server MCP server in PolicyLayer and add a rule for query_prometheus_basic_info: 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 OpenShift OVN-Kubernetes Benchmark MCP Server. Nothing to install.
query_prometheus_basic_info 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 query_prometheus_basic_info 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 query_prometheus_basic_info. 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.
query_prometheus_basic_info is provided by the OpenShift OVN-Kubernetes Benchmark MCP Server MCP server (liqcui/ovnk-benchmark-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 →