Check what ScreenHand knows about an app: shortcuts, selectors, flows, playbooks, error patterns, and stability %. Useful before complex workflows to decide strategy: learn first (if empty), go fast (if high coverage), or use fallback tools (if error patterns exist). Optional for quick actions.
AI agents call coverage_report 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 is a pure read operation that queries the internal state of ScreenHand's knowledge about applications. It has no side effects, does not execute commands, and does not modify or delete data. The tool is explicitly described as 'useful before complex workflows to decide strategy,' confirming its informational purpose.
From the tool's definition The tool 'coverage_report' checks and retrieves information about an app's capabilities ('shortcuts, selectors, flows, playbooks, error patterns, and stability %').
Documented attack patterns abuse exactly the kind of access coverage_report 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 coverage_report:
{
"version": "1",
"default": "deny",
"tools": {
"coverage_report": {}
}
}coverage_report 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.
Check what ScreenHand knows about an app: shortcuts, selectors, flows, playbooks, error patterns, and stability %. Useful before complex workflows to decide strategy: learn first (if empty), go fast (if high coverage), or use fallback tools (if error patterns exist). Optional for quick actions. 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 coverage_report: 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.
coverage_report 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 coverage_report 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 coverage_report. 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.
coverage_report 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.