AI agents call xpath_screenshot to retrieve information from uiautomator2 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots capture visual/UI data without modifying device state or triggering side effects. The empty description lowers confidence slightly, but naming and sibling tools (activity_wait_appear, app_list, etc.) establish this as an Android UI inspection tool. No code execution, data modification, or destructive operations occur. Retrieving screen state is a read operation with minimal blast radius if misused.
From the tool's definition Tool name 'xpath_screenshot' and context indicates it captures screen state for UI inspection via xpath queries, similar to 'screenshot' operations in UI automation frameworks.
Documented attack patterns abuse exactly the kind of access xpath_screenshot 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 xpath_screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"xpath_screenshot": {}
}
}xpath_screenshot is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
xpath_screenshot. It is categorised as a Read tool in the uiautomator2 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the uiautomator2 MCP Server MCP server in PolicyLayer and add a rule for xpath_screenshot: 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.
xpath_screenshot 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 xpath_screenshot 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 xpath_screenshot. 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.
xpath_screenshot 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.