AI agents call list_connected_tools 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 performs a simple enumeration of connected hardware devices without modifying, executing code, or affecting any state. It is a non-destructive query operation with minimal blast radius—an AI agent misusing it would only retrieve information about connected debuggers, not alter or interact with them.
From the tool's definition Tool name 'list_connected_tools' and description 'Return a list of Microchip USB HID debuggers currently attached to the host' indicate a read-only operation that queries and retrieves information about attached devices.
Attacks that exploit this kind of access
Return a list of Microchip USB HID debuggers currently attached to the host. 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 list_connected_tools: 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.
list_connected_tools 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 list_connected_tools 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 list_connected_tools. 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.
list_connected_tools 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 →