Start screen recording
AI agents invoke start_screen_recording to trigger actions in AutoBot MCP. 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 triggers an external operation (screen recording) whose effects depend on when it is stopped and what data is captured. While not destructive or involving financial transactions, it executes an action that could have privacy implications (captures screen contents including sensitive data). It is more severe than a Read operation but less severe than destructive actions.
From the tool's definition Tool 'start_screen_recording' initiates a recording action on an Android device. The description states it will 'Start screen recording', which is an operational trigger that executes a recording process on the device.
Attacks that exploit this kind of access
Start screen recording. It is categorised as a Execute tool in the AutoBot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AutoBot MCP server in PolicyLayer and add a rule for start_screen_recording: 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 AutoBot MCP. Nothing to install.
start_screen_recording 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 start_screen_recording 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 start_screen_recording. 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.
start_screen_recording is provided by the AutoBot MCP server (yz0903/autobot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →