This record as markdown: /tools/io-github-kivanccakmak-yaver/adb-command.md
What adb_command does on Yaver
AI agents invoke adb_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 |
|---|---|---|---|
device | string | — | Device serial (optional) |
command | string | Yes | Shell command |
Parameters from the server's own tool schema.
Why adb_command is rated High
This tool invokes arbitrary command execution on a connected Android device. While the blast radius is limited to the paired mobile device rather than the development host, the ability to run unrestricted commands creates significant risk: an AI agent could install malware, exfiltrate data, modify system settings, or trigger unwanted device operations.
From the tool's definition Tool name 'adb_command' explicitly states it 'Run[s] a command on an Android device via ADB.' ADB (Android Debug Bridge) is a versatile command-line interface that can execute arbitrary commands on connected Android devices, including shell commands, file…
Attacks that exploit this kind of access
The rule that runs adb_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 adb_command, this is the rule to start with:
adb_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every adb_command call is checked against it from then on.
Questions about adb_command
Run a command on an Android device via ADB. 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.
adb_command accepts 2 parameters: device, command. Required: command. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for adb_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.
adb_command 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 adb_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.
Set action: deny in the PolicyLayer policy for adb_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.
adb_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.
More on Yaver, and thousands of servers like it.
Across the catalogue