inspect_at_point
AI agents call inspect_at_point 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.
Based on the naming pattern and server context, 'inspect_at_point' most likely inspects/reads UI element properties at a given screen coordinate, similar to sibling tools like 'inspect_element_tree' and 'get_element_detail'. This would be a Read operation. However, the empty description lowers confidence — it could potentially trigger interactions. Severity is medium given it operates on the desktop UI environment.
From the tool's definition Tool name 'inspect_at_point' on a UI automation server; description is empty and uninformative.
Attacks that exploit this kind of access
inspect_at_point. 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_at_point: 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_at_point 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_at_point 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_at_point. 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_at_point 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 →