Discover connected Victron devices via Modbus TCP by probing unit IDs. Scans a range of unit IDs to find active devices and identify their service type. Modbus only — for MQTT discovery use victron_mqtt_discover instead. This is the first tool you should use with Modbus transport to find what dev...
AI agents call victron_discover 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 network discovery and device enumeration via Modbus TCP, which is a read-only reconnaissance operation. It retrieves information about available devices and their types without modifying, executing commands on, or destructively affecting any system state. The low severity reflects that device discovery has minimal blast radius—it reveals network topology but cannot cause operational harm.
From the tool's definition Tool description states it 'Discover[s] connected Victron devices' by 'probing unit IDs' and 'find[s] active devices and identify[s] their service type'.
Attacks that exploit this kind of access
Discover connected Victron devices via Modbus TCP by probing unit IDs. Scans a range of unit IDs to find active devices and identify their service type. Modbus only — for MQTT discovery use victron_mqtt_discover instead. This is the first tool you should use with Modbus transport to find what devices are available and their unit IDs. 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_discover: 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_discover 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_discover 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_discover. 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_discover 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 →