Executes an ADB command and returns the output or an error. Args: command (str): The ADB shell command to execute Returns: str: The output of the ADB command
AI agents invoke execute_adb_shell_command to trigger actions in Android MCP Server. 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.
This tool allows execution of arbitrary shell commands on an Android device via ADB. While it could theoretically be used for destructive actions (deletion, data wipe) or other operations, the defining characteristic is that it executes code whose side effects are entirely dependent on the command argument—the classical Execute category.
From the tool's definition Tool executes arbitrary ADB shell commands with user-supplied arguments ('command (str): The ADB shell command to execute').
Documented attack patterns abuse exactly the kind of access execute_adb_shell_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Android MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_adb_shell_command:
{
"version": "1",
"default": "deny",
"tools": {
"execute_adb_shell_command": {
"limits": [
{
"counter": "execute_adb_shell_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_adb_shell_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.
Free to start. No card required.
Executes an ADB command and returns the output or an error. Args: command (str): The ADB shell command to execute Returns: str: The output of the ADB command. It is categorised as a Execute tool in the Android MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Android MCP Server MCP server in PolicyLayer and add a rule for execute_adb_shell_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 Android MCP Server. Nothing to install.
execute_adb_shell_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 execute_adb_shell_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 execute_adb_shell_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.
execute_adb_shell_command is provided by the Android MCP Server MCP server (minhalvp/android-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Android MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Android MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.