Get GX generator auto start/stop status and control: manual start/stop command, start condition (SOC/load/voltage/manual), runtime, quiet hours, start/stop state, auto start enabled, service countdown, and alarms. This controls the GX relay-based generator start/stop logic. Unit ID is always 100.
AI agents invoke victron_generator_status to trigger actions in Victron Tcp. 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.
While the tool reads status information, the description explicitly states it includes a 'manual start/stop command' and 'controls' the generator start/stop logic via GX relay. Issuing start/stop commands to a physical generator is an external operation with real-world consequences (starting/stopping electrical generation equipment), placing this firmly in the Execute category.
From the tool's definition 'manual start/stop command' and 'controls the GX relay-based generator start/stop logic'
Attacks that exploit this kind of access
Get GX generator auto start/stop status and control: manual start/stop command, start condition (SOC/load/voltage/manual), runtime, quiet hours, start/stop state, auto start enabled, service countdown, and alarms. This controls the GX relay-based generator start/stop logic. Unit ID is always 100. It is categorised as a Execute tool in the Victron Tcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Victron Tcp MCP server in PolicyLayer and add a rule for victron_generator_status: 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 Victron Tcp. Nothing to install.
victron_generator_status 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 victron_generator_status 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 victron_generator_status. 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.
victron_generator_status is provided by the Victron Tcp MCP server (lubosstrejcek/victron-tcp). 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 →