Screenshot + OCR with detailed region positions (bounds, confidence)
AI agents call ocr_regions 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.
This tool only reads and interprets screen content via OCR. It has no side effects, does not modify state, execute commands, delete data, or move money. It is purely informational, making it a Read category tool. Severity is low because OCR results on screen content present minimal risk—the data extracted is what is already visible to the user.
From the tool's definition Tool performs 'Screenshot + OCR' which retrieves and analyzes visual data from the screen without modifying or executing actions.
Documented attack patterns abuse exactly the kind of access ocr_regions 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_regions:
{
"version": "1",
"default": "deny",
"tools": {
"ocr_regions": {}
}
}ocr_regions 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.
Screenshot + OCR with detailed region positions (bounds, confidence). 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_regions: 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_regions 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_regions 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_regions. 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_regions 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.