AI agents invoke screen_record to trigger actions in uiautomator2 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.
Screen recording on an Android device is an external operation that captures device activity. Given the server's purpose of controlling Android devices and triggering operations, this tool likely initiates a screen recording session. This is an Execute-level action as it triggers an external operation (recording) on the device. It could potentially capture sensitive on-screen information, giving it high severity.
From the tool's definition Tool name 'screen_record' on a server that controls Android devices via uiautomator2; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access screen_record gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and uiautomator2 MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for screen_record:
{
"version": "1",
"default": "deny",
"tools": {
"screen_record": {
"limits": [
{
"counter": "screen_record_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}screen_record 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.
screen_record. It is categorised as a Execute tool in the uiautomator2 MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the uiautomator2 MCP Server MCP server in PolicyLayer and add a rule for screen_record: 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 uiautomator2 MCP Server. Nothing to install.
screen_record 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 screen_record 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 screen_record. 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.
screen_record is provided by the uiautomator2 MCP Server MCP server (tanbro/uiautomator2-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from uiautomator2 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.
77 uiautomator2 MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.