Screenshot a window (or full screen) and OCR it. Returns visible text.
AI agents call screenshot 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.
The screenshot tool captures visual information and extracts text via OCR. This is a read-only operation that retrieves information about the current state of the UI without modifying anything, executing code, or triggering side effects. While it could reveal sensitive information if an agent takes screenshots of confidential content, the tool itself performs no destructive or harmful action.
From the tool's definition Tool description states 'Screenshot a window (or full screen) and OCR it. Returns visible text.' — a purely observational operation with no data modification, deletion, or command execution.
Documented attack patterns abuse exactly the kind of access screenshot 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 screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"screenshot": {}
}
}screenshot 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 a window (or full screen) and OCR it. Returns visible text. 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 screenshot: 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.
screenshot 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 screenshot 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 screenshot. 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.
screenshot 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.