Erase, write, and verify a hex file in one operation.
AI agents call flash 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.
Erase is inherently destructive—it wipes microcontroller firmware irreversibly. Although the tool also writes new code, the erase component cannot be reversed and represents permanent data loss if misapplied. This qualifies as Destructive rather than Execute or Write because the effects are irreversible and the blast radius includes loss of all existing firmware on the device.
From the tool's definition Tool description states 'Erase, write, and verify a hex file in one operation.' The erase operation irreversibly deletes firmware/code from microcontroller memory.
Attacks that exploit this kind of access
Erase, write, and verify a hex file in one operation. 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 flash: 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.
flash 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 flash 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 flash. 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.
flash 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 →