Assign work to a specialist AI agent and track the result. Also known as: hand this off, spawn agent, assign task, delegate to agent, have an AI agent do it.
AI agents use delegate_agent_task to create or update resources in OrgX — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OrgX environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
task | string | — | Task instructions for the target agent |
agent | string | — | Target agent identifier or alias |
context | string | — | Optional supporting context or background for the task |
_context | object | — | Client context for conversation tracking (strongly recommended for cross-client continuity) |
deadline | string | — | Optional due date or plain-text deadline |
initiative_id | string | — | Optional initiative UUID to associate with the spawned task |
initiative_name | string | — | Optional initiative title to resolve automatically if ID is unknown |
style_guidelines | string | — | Optional voice, format, or style constraints |
expected_artifacts | array | — | Optional final outputs you expect |
Parameters from the server's own tool schema.
An AI agent can call delegate_agent_task faster than any human can review — one bad instruction and it creates or modifies resources in OrgX by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (25 properties)
Documented attack patterns abuse exactly the kind of access delegate_agent_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OrgX, and nothing reaches the server without passing your rules. This is the rule we recommend for delegate_agent_task:
{
"version": "1",
"default": "deny",
"tools": {
"delegate_agent_task": {
"limits": [
{
"counter": "delegate_agent_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}delegate_agent_task stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Assign work to a specialist AI agent and track the result. Also known as: hand this off, spawn agent, assign task, delegate to agent, have an AI agent do it. It is categorised as a Write tool in the OrgX MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
delegate_agent_task accepts 9 parameters: task, agent, context, _context, deadline, initiative_id, initiative_name, style_guidelines, expected_artifacts. The full parameter table on this page comes from the server's own tool schema.
Register the OrgX MCP server in PolicyLayer and add a rule for delegate_agent_task: 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 OrgX. Nothing to install.
delegate_agent_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the delegate_agent_task 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 delegate_agent_task. 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.
delegate_agent_task is provided by the OrgX MCP server (useorgx/orgx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 OrgX tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
29 OrgX tools catalogued and risk-classified — across an index of 42,500+ MCP servers.