Start the multi-agent orchestrator daemon. Manages parallel worker slots: web tasks (CDP) run in parallel, native tasks (AX/keyboard) are serialized per-app. Survives restarts.
AI agents invoke orchestrator_start 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 initiates a daemon process that manages execution of web and native automation tasks. Starting a background orchestrator that controls CDP (Chrome DevTools Protocol) sessions and keyboard/accessibility actions is an Execute operation—it triggers external operations whose effects depend on runtime configuration and subsequent agent commands.
From the tool's definition Start the multi-agent orchestrator daemon. Manages parallel worker slots: web tasks (CDP) run in parallel, native tasks (AX/keyboard) are serialized per-app.
Documented attack patterns abuse exactly the kind of access orchestrator_start 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 orchestrator_start:
{
"version": "1",
"default": "deny",
"tools": {
"orchestrator_start": {
"limits": [
{
"counter": "orchestrator_start_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}orchestrator_start 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.
Start the multi-agent orchestrator daemon. Manages parallel worker slots: web tasks (CDP) run in parallel, native tasks (AX/keyboard) are serialized per-app. Survives restarts. 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 orchestrator_start: 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.
orchestrator_start 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 orchestrator_start 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 orchestrator_start. 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.
orchestrator_start 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.