Write a new setpoint value to equipment. Gated by TRANE_ALLOW_SETPOINT_WRITE=true because writes change real HVAC behavior in real buildings. The MCP refuses unless the operator has explicitly authorized writes.
AI agents use set_setpoint to create or update resources in Trane — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trane environment.
This tool creates or modifies data (HVAC setpoint values) reversibly. While the change affects physical systems, setpoint adjustments are not irreversible—they can be overwritten or restored. The gate requiring TRANE_ALLOW_SETPOINT_WRITE=true indicates operator authorization is required, limiting blast radius.
From the tool's definition Tool name 'set_setpoint' and description explicitly states 'Write a new setpoint value to equipment' and 'writes change real HVAC behavior in real buildings.' This modifies operational parameters of building automation systems.
Attacks that exploit this kind of access
Write a new setpoint value to equipment. Gated by TRANE_ALLOW_SETPOINT_WRITE=true because writes change real HVAC behavior in real buildings. The MCP refuses unless the operator has explicitly authorized writes. It is categorised as a Write tool in the Trane MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trane MCP server in PolicyLayer and add a rule for set_setpoint: 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.
set_setpoint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_setpoint 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 set_setpoint. 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.
set_setpoint 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 →