AI agents call storage_partitions to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static information about disk partitions and block devices. It performs a read-only query with no side effects, no code execution, no data modification, and no destructive operations. The blast radius of misuse is minimal—an attacker gains visibility into storage configuration but cannot alter infrastructure or access data directly.
From the tool's definition Tool name 'storage_partitions' and description 'Get disk partition and block device information' indicate querying/retrieval of disk metadata. Uses action verbs 'Get' with no modification, creation, deletion, or execution capability mentioned.
Attacks that exploit this kind of access
Get disk partition and block device information. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for storage_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 Infra Ops. Nothing to install.
storage_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 storage_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 storage_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.
storage_partitions is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →