Submit a task to the orchestrator. Web tasks (CDP) run in parallel, native tasks queue per-app. Returns immediately — task is processed asynchronously.
AI agents invoke orchestrator_submit 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 submits tasks for asynchronous execution — potentially triggering web (CDP browser automation) or native UI actions depending on the task argument. Since it can dispatch arbitrary tasks to an orchestrator controlling the desktop and browser, it spans Execute (and possibly higher categories depending on the task), but Execute is the best fit given the described mechanism.
From the tool's definition Submit a task to the orchestrator. Web tasks (CDP) run in parallel, native tasks queue per-app. Returns immediately — task is processed asynchronously.
Documented attack patterns abuse exactly the kind of access orchestrator_submit 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_submit:
{
"version": "1",
"default": "deny",
"tools": {
"orchestrator_submit": {
"limits": [
{
"counter": "orchestrator_submit_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}orchestrator_submit 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.
Submit a task to the orchestrator. Web tasks (CDP) run in parallel, native tasks queue per-app. Returns immediately — task is processed asynchronously. 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_submit: 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_submit 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_submit 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_submit. 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_submit 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.