AI agents invoke ha_service to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | — | HA URL |
data | object | — | Service data (e.g. {"entity_id": "vacuum.xiaomi", "brightness": 255}) |
token | string | — | HA token |
domain | string | Yes | Service domain (e.g. light, switch, vacuum, climate, scene, automation) |
service | string | Yes | Service name (e.g. turn_on, turn_off, start, set_temperature, toggle) |
Parameters from the server's own tool schema.
ha_service triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts URL/endpoint input (url) · Handles credentials or secrets (token)
Attacks that exploit this kind of access
Call a Home Assistant service — turn on/off lights, start vacuum, set thermostat, trigger scenes. Works with Xiaomi, Hue, IKEA, and all HA integrations. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
ha_service accepts 5 parameters: url, data, token, domain, service. Required: domain, service. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for ha_service: 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.
ha_service is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ha_service 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 ha_service. 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.
ha_service 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.