inspect_element_tree
AI agents call inspect_element_tree to retrieve information from Uiautomation without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool inspects and retrieves information about Windows UI element hierarchies without modifying or executing any actions on them. This is a read-only operation that gathers data about the current state of the desktop UI.
From the tool's definition Tool name 'inspect_element_tree' and server description indicates inspection of UI trees and properties. Paired with other sibling tools like 'capture_screenshot', 'get_element_detail', and 'find_elements', this is clearly a reconnaissance/inspection tool…
Attacks that exploit this kind of access
inspect_element_tree. It is categorised as a Read tool in the Uiautomation MCP Server, which means it retrieves data without modifying state.
Register the Uiautomation MCP server in PolicyLayer and add a rule for inspect_element_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 Uiautomation. Nothing to install.
inspect_element_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 inspect_element_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 inspect_element_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.
inspect_element_tree is provided by the Uiautomation MCP server (miloira/uiautomation-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 →