AI agents invoke adb_shell to trigger actions in ADB 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.
ADB shell provides arbitrary shell command execution on Android devices. Despite the empty description, the tool name combined with the server's stated purpose of 'shell command execution' makes it clear this executes arbitrary shell commands. This is critical severity because unrestricted shell access can read/write/delete any file, install malware, exfiltrate data, or brick the device.
From the tool's definition Tool name 'adb_shell' on a server described as enabling 'shell command execution' through ADB commands
Documented attack patterns abuse exactly the kind of access adb_shell gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ADB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for adb_shell:
{
"version": "1",
"default": "deny",
"tools": {
"adb_shell": {
"limits": [
{
"counter": "adb_shell_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}adb_shell 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.
adb_shell. It is categorised as a Execute tool in the ADB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for adb_shell: 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 ADB MCP Server. Nothing to install.
adb_shell 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_shell 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_shell. 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_shell is provided by the ADB MCP Server MCP server (srmorete/adb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 ADB MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 ADB MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.