Capture screenshot, UI hierarchy, and basic device metadata together.
AI agents call android_capture_state to retrieve information from DevLab MCP Suite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/captures the current visual and structural state of the device (screenshot, UI hierarchy, device metadata). It has no side effects, does not modify data, and cannot cause harm beyond information disclosure about the device's current state.
From the tool's definition Capture screenshot, UI hierarchy, and basic device metadata together
Attacks that exploit this kind of access
Capture screenshot, UI hierarchy, and basic device metadata together. It is categorised as a Read tool in the DevLab MCP Suite MCP Server, which means it retrieves data without modifying state.
Register the DevLab MCP Suite MCP server in PolicyLayer and add a rule for android_capture_state: 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 DevLab MCP Suite. Nothing to install.
android_capture_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the android_capture_state 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 android_capture_state. 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.
android_capture_state is provided by the DevLab MCP Suite MCP server (tanguito86/devlab-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 →