Register a watch rule: when element with matching title appears, execute an action. Use for automated responses to known UI states.
AI agents invoke watch_register 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 sets up automated execution: when a UI element matching a condition appears, it fires an action automatically. The core behavior is executing actions (potentially UI interactions, scripts, or commands) triggered by UI state changes. This is Execute-category because it runs operations whose effects depend on the registered rule and action arguments.
From the tool's definition 'execute an action' and 'automated responses to known UI states' — the tool registers a trigger that automatically executes actions when UI conditions are met
Documented attack patterns abuse exactly the kind of access watch_register 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 watch_register:
{
"version": "1",
"default": "deny",
"tools": {
"watch_register": {
"limits": [
{
"counter": "watch_register_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}watch_register 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.
Register a watch rule: when element with matching title appears, execute an action. Use for automated responses to known UI states. 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 watch_register: 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.
watch_register 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 watch_register 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 watch_register. 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.
watch_register 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.