get_text_from_rectangle_of_screen
AI agents call get_text_from_rectangle_of_screen to retrieve information from Vnc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves text from a defined screen area via OCR without modifying the desktop or executing actions. It is a read-only operation with no side effects. Confidence is slightly reduced (0.85 not 0.95) due to empty description, but the name and server context make the intent clear.
From the tool's definition Tool name 'get_text_from_rectangle_of_screen' indicates text retrieval from a screen region; sibling tools include 'get_text_from_whole_screen_image' (clearly Read) and 'get_whole_screen_image' (retrieval without modification).
Documented attack patterns abuse exactly the kind of access get_text_from_rectangle_of_screen gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vnc, and nothing reaches the server without passing your rules. This is the rule we recommend for get_text_from_rectangle_of_screen:
{
"version": "1",
"default": "deny",
"tools": {
"get_text_from_rectangle_of_screen": {}
}
}get_text_from_rectangle_of_screen 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.
get_text_from_rectangle_of_screen. It is categorised as a Read tool in the Vnc MCP Server, which means it retrieves data without modifying state.
Register the Vnc MCP server in PolicyLayer and add a rule for get_text_from_rectangle_of_screen: 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 Vnc. Nothing to install.
get_text_from_rectangle_of_screen 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_text_from_rectangle_of_screen 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_text_from_rectangle_of_screen. 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_text_from_rectangle_of_screen is provided by the Vnc MCP server (regulad/vnc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vnc, 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.
20 Vnc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.