AI agents call get_ui_tree to retrieve information from Phantom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the UI hierarchy/structure from a running app on a simulator or device. It is a read-only operation that extracts information about the current UI tree for inspection and testing purposes. No data is created, modified, or deleted; no commands are executed with side effects. The low severity reflects minimal risk—misuse would only expose app UI structure information, not cause system harm.
From the tool's definition The tool name 'get_ui_tree' and partial description 'Retourne l' (returns/retrieves in French) indicate a retrieval operation that queries the UI structure of a mobile device without modifying state.
Attacks that exploit this kind of access
Retourne l. It is categorised as a Read tool in the Phantom MCP Server, which means it retrieves data without modifying state.
Register the Phantom MCP server in PolicyLayer and add a rule for get_ui_tree: 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 Phantom. Nothing to install.
get_ui_tree 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 get_ui_tree 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 get_ui_tree. 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.
get_ui_tree is provided by the Phantom MCP server (nthimpulse/phantom-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 →