onewire_read · Buspirate MCP: Risk & Policy

WHAT IT DOES

What onewire_read does on Buspirate

AI agents invoke onewire_read 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.

WHY IT NEEDS A POLICY

Why onewire_read needs a policy

This tool both writes arbitrary bytes to and reads from a physical 1-Wire hardware bus. Since it sends arbitrary data to external hardware (which could trigger device state changes, commands, or configuration writes on connected 1-Wire devices), it goes beyond a pure read operation. The 'send arbitrary bytes' aspect makes it Execute-level, as the effects depend on what bytes are sent to the hardware.

From the tool's definition Send arbitrary bytes on the 1-Wire bus and read back a response

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

onewire_read Rate-limited

onewire_read stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "onewire_read": {
      "limits": [
        {
          "counter": "onewire_read_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Buspirate, so you can run agents against it safely.

FAQ

Questions about onewire_read

What does the onewire_read tool do? +

Send arbitrary bytes on the 1-Wire bus and read back a response. 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.

How do I enforce a policy on onewire_read? +

Register the Buspirate MCP server in PolicyLayer and add a rule for onewire_read: 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.

What risk level is onewire_read? +

onewire_read is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit onewire_read? +

Yes. Add a rate_limit block to the onewire_read 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.

How do I block onewire_read completely? +

Set action: deny in the PolicyLayer policy for onewire_read. 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.

What MCP server provides onewire_read? +

onewire_read 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.