AI agents invoke spi_transfer to trigger actions in Buspirate. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool sends raw SPI transactions to hardware devices, which can trigger arbitrary hardware operations depending on the target device (e.g., writing firmware, modifying flash memory, controlling peripherals). While it has a read-back option, the primary action is executing hardware-level commands whose effects are entirely dependent on the connected device and bytes sent.
From the tool's definition 'Send a raw SPI transaction. Write hex bytes and optionally read back.'
Attacks that exploit this kind of access
Send a raw SPI transaction. Write hex bytes and optionally read back. It is categorised as a Execute tool in the Buspirate MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Buspirate MCP server in PolicyLayer and add a rule for spi_transfer: 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_transfer is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the spi_transfer 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_transfer. 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_transfer 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 →