Write a binary file to SPI flash. Optionally erases first and verifies.
AI agents call spi_write to permanently remove resources in Buspirate — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Writing to SPI flash is inherently destructive: the optional erase phase wipes existing flash contents irreversibly, and overwriting firmware or bootloader data on embedded hardware can render a device unbootable. Even without the erase, overwriting SPI flash data is not easily reversible.
From the tool's definition 'Write a binary file to SPI flash. Optionally erases first and verifies.' — the erase operation is irreversible, and overwriting firmware/data on SPI flash can permanently brick a device or destroy stored data.
Attacks that exploit this kind of access
Write a binary file to SPI flash. Optionally erases first and verifies. It is categorised as a Destructive tool in the Buspirate MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Buspirate MCP server in PolicyLayer and add a rule for spi_write: 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 Buspirate. Nothing to install.
spi_write 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 spi_write 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 spi_write. 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.
spi_write is provided by the Buspirate MCP server (mplogas/buspirate-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 →