AI agents call read_screen_text to retrieve information from Uitars without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries visual text data from the screen without modifying, executing, or destructing anything. It is purely informational, making it a Read category tool. Severity is low because screen text reading carries minimal risk unless sensitive credentials are displayed, which would depend on context rather than the tool's inherent capability.
From the tool's definition Tool name 'read_screen_text' and description 'Read all text visible on screen' directly indicate a read operation with no data modification, creation, or side effects.
Attacks that exploit this kind of access
Read all text visible on screen. It is categorised as a Read tool in the Uitars MCP Server, which means it retrieves data without modifying state.
Register the Uitars MCP server in PolicyLayer and add a rule for read_screen_text: 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 Uitars. Nothing to install.
read_screen_text 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 read_screen_text 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 read_screen_text. 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.
read_screen_text is provided by the Uitars MCP server (lxsoftroxs/uitars-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
read_screen_text is one line of Uitars's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →