Read text content from the screen or a specific element using the canonical fallback chain: AX → CDP → OCR. Returns the text found.
AI agents call read_with_fallback 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 retrieves and queries text data from the screen or UI elements without creating, modifying, deleting, or executing anything. It has no side effects beyond reading. While it could enable reconnaissance in a multi-step attack, reading text alone is the lowest-severity risk category.
From the tool's definition Tool name contains 'read' and description states 'Read text content from the screen or a specific element' and 'Returns the text found.' The fallback chain (AX → CDP → OCR) are all text retrieval mechanisms with no modification or execution capabilities.
Documented attack patterns abuse exactly the kind of access read_with_fallback 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 read_with_fallback:
{
"version": "1",
"default": "deny",
"tools": {
"read_with_fallback": {}
}
}read_with_fallback 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.
Read text content from the screen or a specific element using the canonical fallback chain: AX → CDP → OCR. Returns the text found. 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 read_with_fallback: 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.
read_with_fallback 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 read_with_fallback 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 read_with_fallback. 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.
read_with_fallback 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.