get_ocp_node_usage
AI agents call get_ocp_node_usage to retrieve information from OCP Performance Analyzer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix and node usage monitoring context indicate this tool retrieves cluster metrics without modification or execution capabilities. Even without a description, the operational context of a performance analyzer platform and similarity to sibling tools (get_etcd_cluster_status, get_api_server_stats, get_egressip_status) strongly indicates read-only telemetry retrieval.
From the tool's definition Tool name 'get_ocp_node_usage' uses 'get' prefix and queries node usage metrics, consistent with retrieval operations.
Attacks that exploit this kind of access
get_ocp_node_usage. It is categorised as a Read tool in the OCP Performance Analyzer MCP MCP Server, which means it retrieves data without modifying state.
Register the OCP Performance Analyzer MCP server in PolicyLayer and add a rule for get_ocp_node_usage: 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 OCP Performance Analyzer MCP. Nothing to install.
get_ocp_node_usage 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_ocp_node_usage 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_ocp_node_usage. 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_ocp_node_usage is provided by the OCP Performance Analyzer MCP server (openshift-eng/ocp-performance-analyzer-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 →