device_broadcast_command

SERVERYaver SOURCEyaver-cli

High RISK CLASS

Category Execute

Parameters 31 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-kivanccakmak-yaver/device-broadcast-command.md

WHAT IT DOES

What device_broadcast_command does on Yaver

AI agents invoke device_broadcast_command to trigger actions in Yaver. 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
`data`	object	—	Optional command payload passed through verbatim to the SDK listener.
`command`	string	Yes	BlackBox command name — what the SDK listener acts on (e.g. "reload", "reload_bundle", "open_app").
`target_device_id`	string	—	When set, scoped to that one SDK session. Empty/omitted = broadcast to all subscribed devices.

Parameters from the server's own tool schema.

RISK

Why device_broadcast_command is rated High

This tool remotely executes commands on physical devices (or broadcasts to all paired devices), triggering external operations like reloading bundles or opening apps. The broadcast capability means a single call can affect all paired devices simultaneously, making the blast radius high if misused.

From the tool's definition Push a BlackBox command directly to a paired SDK device (or broadcast to all)... Examples of useful commands: 'reload', 'reload_bundle', 'open_app'

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs device_broadcast_command safely

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

device_broadcast_command Rate-limited

device_broadcast_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_broadcast_command": {
      "limits": [
        {
          "counter": "device_broadcast_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 Yaver, apply this rule, and every device_broadcast_command call is checked against it from then on.

FAQ

Questions about device_broadcast_command

What does the device_broadcast_command tool do? +

Push a BlackBox command directly to a paired SDK device (or broadcast to all) without needing an active dev-server. This is the Path-C/8 fallback for the cross-device reload workflow: Phone A drives, Phone B receives, no Metro bundler involved — both phones just share a Yaver agent (managed-cloud, self-hosted, or local). Examples of useful commands: "reload", "reload_bundle", "open_app". Returns { ok, mode: "scoped"|"broadcast"|"no_blackbox", targetDeviceId?, reachedSession? }. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does device_broadcast_command accept? +

device_broadcast_command accepts 3 parameters: data, command, target_device_id. Required: command. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on device_broadcast_command? +

Register the Yaver MCP server in PolicyLayer and add a rule for device_broadcast_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 Yaver. Nothing to install.

What risk level is device_broadcast_command? +

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

Can I rate-limit device_broadcast_command? +

Yes. Add a rate_limit block to the device_broadcast_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_broadcast_command completely? +

Set action: deny in the PolicyLayer policy for device_broadcast_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_broadcast_command? +

device_broadcast_command is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Yaver, and thousands of servers like it.

This server

All 645 Yaver tools → High-risk tools on this server →

Across the catalogue

adb_backup_device on Android Forensics ADB MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

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