Create, approve, reject, remember, or list durable OrgX decisions. Per-action input requirements: • action="list_pending" → No required fields. Optional: initiative_id, workspace_id (scope filters). • action="create" → REQUIRES title AND decision (the resolved decision text). Recommended: context...
AI agents use orgx_decide 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 |
|---|---|---|---|
note | string | — | Optional approver note for action=approve. Free-text rationale stored in audit history. |
title | string | — | Short title for the decision. REQUIRED for action=create. |
action | string | — | Decision operation. See top-level description for per-action required fields. |
reason | string | — | REQUIRED for action=reject. Explanation of why the decision was rejected — used by the assigned agent to adjust its next attempt. |
context | string | — | Background context / rationale that led to the decision. Recommended for action=create to capture provenance. |
summary | string | — | Optional one-line summary used in lists. Falls back to title when omitted. |
_context | object | — | Client context for conversation tracking (strongly recommended for cross-client continuity) |
decision | string | — | The decision text itself (what was decided). REQUIRED for action=create and action=remember. |
session_id | string | — | Optional bootstrap/session identifier returned by orgx_bootstrap. |
decision_id | string | — | Decision UUID. REQUIRED for action=approve or action=reject. Returned by action=list_pending or action=create. |
workspace_id | string | — | Optional workspace UUID to scope the decision. Defaults to the MCP session's workspace. |
initiative_id | string | — | Optional initiative UUID to scope the decision. Used as filter when action=list_pending; used as parent when action=create. |
Parameters from the server's own tool schema.
An AI agent can call orgx_decide 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 (29 properties)
Documented attack patterns abuse exactly the kind of access orgx_decide 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 orgx_decide:
{
"version": "1",
"default": "deny",
"tools": {
"orgx_decide": {
"limits": [
{
"counter": "orgx_decide_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}orgx_decide 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.
Create, approve, reject, remember, or list durable OrgX decisions. Per-action input requirements: • action="list_pending" → No required fields. Optional: initiative_id, workspace_id (scope filters). • action="create" → REQUIRES title AND decision (the resolved decision text). Recommended: context, initiative_id. • action="remember" → REQUIRES decision (the text to capture as a remembered decision). Optional: title, context. • action="approve" → REQUIRES decision_id. Optional: note (free-text approver rationale). • action="reject" → REQUIRES decision_id AND reason (explanation shown to the assigned agent). USE WHEN: capturing judgment, approval, rejection, or pending decision review. NEXT: use orgx_act, orgx_write, or orgx_spawn only after the decision resolves the next action. DO NOT USE WHEN: writing non-decision entities; use orgx_write. 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.
orgx_decide accepts 12 parameters: note, title, action, reason, context, summary, _context, decision, session_id, decision_id, workspace_id, initiative_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 orgx_decide: 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.
orgx_decide 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 orgx_decide 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 orgx_decide. 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.
orgx_decide 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.