OCR a window with element positions. SLOW — prefer ui_tree for structured element discovery. Use OCR only for reading visual/canvas content.
AI agents call ocr to retrieve information from ScreenHand without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
OCR (Optical Character Recognition) performs visual content recognition without modifying, executing, or deleting anything. It retrieves and interprets text/visual information from windows. The tool has no side effects and poses minimal risk—at worst, an AI agent could read information it shouldn't have access to, but cannot directly harm systems or data through this tool alone.
From the tool's definition The description states the tool is for 'OCR a window' and explicitly recommends it only for 'reading visual/canvas content.' The instruction 'prefer ui_tree for structured element discovery' confirms it is a read-only operation.
Documented attack patterns abuse exactly the kind of access ocr gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for ocr:
{
"version": "1",
"default": "deny",
"tools": {
"ocr": {}
}
}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 a window with element positions. SLOW — prefer ui_tree for structured element discovery. Use OCR only for reading visual/canvas content. It is categorised as a Read tool in the ScreenHand MCP Server, which means it retrieves data without modifying state.
Register the ScreenHand MCP server in PolicyLayer and add a rule for 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 ScreenHand. Nothing to install.
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 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 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.
ocr is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, 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.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.