List all partitions on a CPC/system
AI agents call list_partitions to retrieve information from zRobot WSAPI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
list_partitions retrieves and enumerates partition data from IBM Z hardware systems. This is a Read operation as it queries system state without side effects. Severity is medium rather than low because the returned partition data could include sensitive configuration details about enterprise hardware infrastructure (names, states, resource allocations), which could inform further attacks.
From the tool's definition Tool name and description indicate it 'List all partitions on a CPC/system' – a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
List all partitions on a CPC/system. It is categorised as a Read tool in the zRobot WSAPI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the zRobot WSAPI MCP Server MCP server in PolicyLayer and add a rule for list_partitions: 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 zRobot WSAPI MCP Server. Nothing to install.
list_partitions 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 list_partitions 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 list_partitions. 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.
list_partitions is provided by the zRobot WSAPI MCP Server MCP server (thirrukumar/zrobot-wsapi-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 →