erase
AI agents call erase to permanently remove resources in Pymcuprog — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An erase operation on a microcontroller is irreversible—once executed, the erased memory contents cannot be recovered. An AI agent misusing this tool could permanently corrupt a device's firmware or data. This is the most severe class of action. The empty description lowers confidence slightly, but the tool name combined with the server context (hardware programming) leaves little ambiguity.
From the tool's definition Tool named 'erase' with no description, on a microcontroller programming server (pymcuprog-mcp) alongside flash/read_memory operations. Erase operations on microcontrollers irreversibly delete firmware and data from non-volatile memory.
Attacks that exploit this kind of access
erase. It is categorised as a Destructive tool in the Pymcuprog MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pymcuprog MCP server in PolicyLayer and add a rule for erase: 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.
erase is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the erase 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 erase. 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.
erase 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 →