Appelle un service Home Assistant pour contrôler des appareils
AI agents invoke call_service to trigger actions in Home Assistant MCP Server. 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.
This tool triggers external operations by calling Home Assistant services, which can control physical smart home devices (lights, locks, thermostats, alarms, etc.). The effects depend on arguments passed and can range from benign (turning on a light) to impactful (unlocking doors, disabling alarms).
From the tool's definition "Appelle un service Home Assistant pour contrôler des appareils" (Calls a Home Assistant service to control devices)
Attacks that exploit this kind of access
Appelle un service Home Assistant pour contrôler des appareils. It is categorised as a Execute tool in the Home Assistant MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Home Assistant MCP Server MCP server in PolicyLayer and add a rule for call_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 Home Assistant MCP Server. Nothing to install.
call_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 call_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 call_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.
call_service is provided by the Home Assistant MCP Server MCP server (jonathan97480/mcphomeassistant). 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 →