Recommend what should happen next based on progress gaps, blockers, and execution templates. Also known as: next best action, prioritize work, unblock project. USE WHEN: user asks what to do next, or needs help prioritizing. NEXT: Execute the recommended action (entity_action, spawn_agent_task, e...
AI agents invoke recommend_next_action to trigger actions in OrgX. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Max recommendations to return (default 5, max 5) |
cascade | boolean | — | If true, refresh recommendations across the entity chain first |
_context | object | — | Client context for conversation tracking (strongly recommended for cross-client continuity) |
entity_id | string | — | Entity ID. For workspace, use "default" or a workspace ID. |
entity_type | string | — | Entity type to recommend for (default: workspace) |
workspace_id | string | — | Optional workspace ID to scope recommendations (canonical). |
command_center_id | string | — | Deprecated alias for workspace_id. |
Parameters from the server's own tool schema.
recommend_next_action triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsHigh parameter count (23 properties)
Documented attack patterns abuse exactly the kind of access recommend_next_action 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 recommend_next_action:
{
"version": "1",
"default": "deny",
"tools": {
"recommend_next_action": {
"limits": [
{
"counter": "recommend_next_action_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}recommend_next_action 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.
Recommend what should happen next based on progress gaps, blockers, and execution templates. Also known as: next best action, prioritize work, unblock project. USE WHEN: user asks what to do next, or needs help prioritizing. NEXT: Execute the recommended action (entity_action, spawn_agent_task, etc.). DO NOT USE: when user already knows what they want to do. Read-only. It is categorised as a Execute tool in the OrgX MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
recommend_next_action accepts 7 parameters: limit, cascade, _context, entity_id, entity_type, workspace_id, command_center_id. 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 recommend_next_action: 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.
recommend_next_action 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 recommend_next_action 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 recommend_next_action. 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.
recommend_next_action 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.