AI agents invoke trigger_flow to trigger actions in HomeyPro 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.
Triggering a flow in a home automation system executes pre-defined automation sequences whose effects depend on what the flow contains. This is an Execute category tool because it runs automation logic with real-world side effects (device control). Severity is high because misconfigured or malicious flow execution could disrupt home operations, lock/unlock doors, or affect physical security.
From the tool's definition Tool name 'trigger_flow' indicates execution of automation flows in a home automation system. The description is empty, but the name clearly denotes triggering/executing a flow.
Documented attack patterns abuse exactly the kind of access trigger_flow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HomeyPro MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for trigger_flow:
{
"version": "1",
"default": "deny",
"tools": {
"trigger_flow": {
"limits": [
{
"counter": "trigger_flow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}trigger_flow stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
trigger_flow. It is categorised as a Execute tool in the HomeyPro MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the HomeyPro MCP Server MCP server in PolicyLayer and add a rule for trigger_flow: 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 HomeyPro MCP Server. Nothing to install.
trigger_flow 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 trigger_flow 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 trigger_flow. 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.
trigger_flow is provided by the HomeyPro MCP Server MCP server (pigmej/python-homey-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from HomeyPro MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 HomeyPro MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.