AI agents call list_equipment to retrieve information from Trane without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries equipment inventory from a building automation system without creating, modifying, deleting, or executing operations. The use case ('scoping work') confirms it supports informational lookup only. Even if an AI agent misuses this tool by listing equipment repeatedly, the blast radius is minimal—no systems are altered, no financial obligations incurred, and no code is executed.
From the tool's definition Tool name 'list_equipment' and description 'List HVAC equipment at a building' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
List HVAC equipment at a building (AHUs, chillers, boilers, VAV boxes, fan coils, etc.). Used by an agent scoping work for a building. It is categorised as a Read tool in the Trane MCP Server, which means it retrieves data without modifying state.
Register the Trane MCP server in PolicyLayer and add a rule for list_equipment: 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 Trane. Nothing to install.
list_equipment 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_equipment 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_equipment. 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_equipment is provided by the Trane MCP server (nobanks/trane-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 →