AI agents call onewire_search to retrieve information from Buspirate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs device discovery on a 1-Wire bus by issuing a standard Read ROM command (0x33), which is a non-invasive query that enumerates devices. It has no side effects, does not modify device state, and does not execute arbitrary code or commands. The blast radius of misuse is minimal — an attacker could only discover what 1-Wire devices are present, which is informational. It belongs in the Read category.
From the tool's definition Tool name contains 'search' and description states 'Search for a device on the 1-Wire bus' — a query operation that discovers connected devices without modifying state or triggering device operations.
Attacks that exploit this kind of access
Search for a device on the 1-Wire bus using Read ROM (0x33). It is categorised as a Read tool in the Buspirate MCP Server, which means it retrieves data without modifying state.
Register the Buspirate MCP server in PolicyLayer and add a rule for onewire_search: 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.
onewire_search 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 onewire_search 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 onewire_search. 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.
onewire_search 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 →