OCR the screen using Apple Vision. Returns every text element with pixel coordinates (x, y, centerX, centerY). Use centerX/centerY with click_at to click on any text.
AI agents call screen_ocr to retrieve information from Macos Control without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/captures the current screen content and returns text with coordinates. It has no side effects itself—it only retrieves visual data. However, severity is medium because it can expose sensitive on-screen information (passwords, private data, confidential documents) to an AI agent.
From the tool's definition OCR the screen using Apple Vision. Returns every text element with pixel coordinates
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access screen_ocr gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Macos Control, and nothing reaches the server without passing your rules. This is the rule we recommend for screen_ocr:
{
"version": "1",
"default": "deny",
"tools": {
"screen_ocr": {}
}
}screen_ocr 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.
OCR the screen using Apple Vision. Returns every text element with pixel coordinates (x, y, centerX, centerY). Use centerX/centerY with click_at to click on any text. It is categorised as a Read tool in the Macos Control MCP Server, which means it retrieves data without modifying state.
Register the Macos Control MCP server in PolicyLayer and add a rule for screen_ocr: 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 Macos Control. Nothing to install.
screen_ocr 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 screen_ocr 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 screen_ocr. 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.
screen_ocr is provided by the Macos Control MCP server (peterhdd/macos-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Macos Control, 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.
22 Macos Control tools catalogued and risk-classified — across an index of 43,000+ MCP servers.