AI agents call agent_machine_inventory to retrieve information from Yaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though agent_machine_inventory only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
List Yaver mesh machines with online state, hardware slots, runner readiness, and machine profile signatures so an MCP client can choose a machine pool. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
Register the Yaver MCP server in PolicyLayer and add a rule for agent_machine_inventory: 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 Yaver. Nothing to install.
agent_machine_inventory 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 agent_machine_inventory 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 agent_machine_inventory. 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.
agent_machine_inventory is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.