AI agents call scan_registers to retrieve information from Kc Modbus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Scanning registers for non-zero values is a read-only operation that retrieves data from PLC memory without side effects. It does not create, modify, delete, or execute operations. The low severity reflects minimal blast radius—scanning is a passive reconnaissance activity typical of monitoring industrial devices.
From the tool's definition Tool name 'scan_registers' and description 'Scan a range of holding registers for non-zero values' indicate a query/retrieval operation that examines register states without modification. No writes, deletes, or external execution described.
Attacks that exploit this kind of access
Scan a range of holding registers for non-zero values. It is categorised as a Read tool in the Kc Modbus MCP Server, which means it retrieves data without modifying state.
Register the Kc Modbus MCP server in PolicyLayer and add a rule for scan_registers: 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 Kc Modbus. Nothing to install.
scan_registers 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 scan_registers 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 scan_registers. 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.
scan_registers is provided by the Kc Modbus MCP server (kerberosclaw/kc_modbus_mcp). 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 →