AI agents invoke record_screen to trigger actions in Adb. 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.
Screen recording initiates an external operation on the device that captures ongoing activity. It is not a simple read (it actively starts a recording process with side effects), not destructive, not financial. Execute best fits as it triggers an external operation whose effects depend on arguments (duration, output path, etc.). Misuse could capture sensitive on-screen data, making severity medium.
From the tool's definition 录制设备屏幕 (Record device screen) — triggers an active screen recording operation on the Android device via ADB
Documented attack patterns abuse exactly the kind of access record_screen gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Adb, and nothing reaches the server without passing your rules. This is the rule we recommend for record_screen:
{
"version": "1",
"default": "deny",
"tools": {
"record_screen": {
"limits": [
{
"counter": "record_screen_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}record_screen 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.
录制设备屏幕. It is categorised as a Execute tool in the Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adb MCP server in PolicyLayer and add a rule for record_screen: 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. Nothing to install.
record_screen 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 record_screen 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 record_screen. 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.
record_screen is provided by the Adb MCP server (wolfcoming/adb_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Adb, 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.
48 Adb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.