Stop recording and save the captured actions as a new playbook.
AI agents invoke recording_stop to trigger actions in ScreenHand. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes the action of stopping a recording session and persisting captured UI automation sequences as a playbook file. While superficially a 'save' operation (Write category), the artifact being saved is a series of executable automation commands that can be replayed to control desktop applications and browser sessions.
From the tool's definition Tool performs 'Stop recording and save the captured actions as a new playbook'—this records and persists a sequence of desktop automation actions that can be replayed to control applications, interact with browsers, and manipulate UI state.
Documented attack patterns abuse exactly the kind of access recording_stop 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_stop:
{
"version": "1",
"default": "deny",
"tools": {
"recording_stop": {
"limits": [
{
"counter": "recording_stop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}recording_stop stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Stop recording and save the captured actions as a new playbook. It is categorised as a Execute tool in the ScreenHand MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScreenHand MCP server in PolicyLayer and add a rule for recording_stop: 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_stop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the recording_stop 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_stop. 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_stop 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.