Check if recording is active and how many events captured so far.
AI agents call recording_status 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 performs a passive read operation to check the state of a recording system and retrieve a count of captured events. It has no side effects, does not execute commands, and does not modify any data. It is purely informational and belongs in the Read category with low severity since misuse would at most expose metadata about recorded UI interactions.
From the tool's definition Tool name 'recording_status' and description 'Check if recording is active and how many events captured so far' indicates a query operation that retrieves status information without modifying or executing any actions.
Documented attack patterns abuse exactly the kind of access recording_status 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 recording_status:
{
"version": "1",
"default": "deny",
"tools": {
"recording_status": {}
}
}recording_status 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 if recording is active and how many events captured so far. 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 recording_status: 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.
recording_status 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 recording_status 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 recording_status. 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.
recording_status 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.