device.registry.command

SERVERApibase SOURCEapibase-mcp-client

High RISK CLASS

Category Execute

Parameters 54 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-whiteknightonhorse-apibase/device.registry.command.md

WHAT IT DOES

What device.registry.command does on Apibase

AI agents invoke device.registry.command to trigger actions in Apibase. 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.

Parameter	Type	Required	Description
`value`	string \| number \| boolean	Yes	The value to set for this command
`command`	string	Yes	The device's data-point code, e.g. 'switch_1', 'temp_set'
`confirm`	boolean	—	Must be true for any device class flagged confirm_required in the safety layer (locks, valves, etc.)
`device_id`	string	Yes	The vendor's device id (from device.list)
`connection_id`	string	Yes	Your device-connection id from /connect/device/connections

Parameters from the server's own tool schema.

RISK

Why device.registry.command is rated High

Executes commands on physical devices with real-world consequences that may be irreversible or dangerous.

From the tool's definition Send a command to a physical device, turn plug on/off, set AC temperature

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs device.registry.command safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Apibase, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For device.registry.command, this is the rule to start with:

device.registry.command Rate-limited

device.registry.command 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": {
    "device.registry.command": {
      "limits": [
        {
          "counter": "device.registry.command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Apibase, apply this rule, and every device.registry.command call is checked against it from then on.

FAQ

Questions about device.registry.command

What does the device.registry.command tool do? +

⚡ ACTION: Send a command to a physical device the calling agent owns via a linked vendor connection (e.g. turn a plug on/off, set an AC temperature). Numeric setpoints are bounds-checked against the device class's configured safety limits (config/device-classes.json); some device classes require confirm:true. Requires connection_id, device_id, command, value. It is categorised as a Execute tool in the Apibase MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does device.registry.command accept? +

device.registry.command accepts 5 parameters: value, command, confirm, device_id, connection_id. Required: value, command, device_id, connection_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on device.registry.command? +

Register the Apibase MCP server in PolicyLayer and add a rule for device.registry.command: 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 Apibase. Nothing to install.

What risk level is device.registry.command? +

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

Can I rate-limit device.registry.command? +

Yes. Add a rate_limit block to the device.registry.command 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 device.registry.command completely? +

Set action: deny in the PolicyLayer policy for device.registry.command. 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 device.registry.command? +

device.registry.command is provided by the Apibase MCP server (apibase-mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Apibase, and thousands of servers like it.

This server

All 1384 Apibase tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →