Read all registers for any Victron device category by service name. Covers all 33 categories including digital inputs, genset, PV inverter, settings, GPS, meteo, and more. Use victron_discover to find connected devices and their unit IDs first.
AI agents call victron_read_category to retrieve information from Victron Tcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval only—it queries registers from connected Victron devices to fetch monitoring data (solar, battery, grid, inverter status). There are no side effects, no data modification, no code execution, and no financial implications. The sibling tools (victron_acload_status, victron_battery_status, etc.) further confirm the read-only nature of this server's functionality.
From the tool's definition Tool name contains 'read' and description states 'Read all registers for any Victron device category'. The function retrieves real-time data from Victron Energy systems without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Read all registers for any Victron device category by service name. Covers all 33 categories including digital inputs, genset, PV inverter, settings, GPS, meteo, and more. Use victron_discover to find connected devices and their unit IDs first. It is categorised as a Read tool in the Victron Tcp MCP Server, which means it retrieves data without modifying state.
Register the Victron Tcp MCP server in PolicyLayer and add a rule for victron_read_category: 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_read_category is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the victron_read_category 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_read_category. 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_read_category 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 →