AI agents call read_supply_voltage to retrieve information from Pymcuprog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a voltage measurement or configuration value from the debugger hardware. It performs no modifications, executions, or destructive actions. Reading a voltage setpoint is a passive query with no capability to affect system state or trigger external operations. The blast radius of misuse is minimal—an AI agent could only obtain harmless telemetry data about the debugger's power supply configuration.
From the tool's definition Tool name is 'read_supply_voltage' and description states 'Read the debugger's onboard supply voltage setpoint' — clearly a read operation with no side effects.
Attacks that exploit this kind of access
Read the debugger's onboard supply voltage setpoint. It is categorised as a Read tool in the Pymcuprog MCP Server, which means it retrieves data without modifying state.
Register the Pymcuprog MCP server in PolicyLayer and add a rule for read_supply_voltage: 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 Pymcuprog. Nothing to install.
read_supply_voltage 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 read_supply_voltage 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 read_supply_voltage. 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.
read_supply_voltage is provided by the Pymcuprog MCP server (lucasgerads/pymcuprog-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 →