run_onboarding_workflow

THE RISK

High Risk

Why run_onboarding_workflow needs a policy

This is an Execute action because it triggers an external operation (onboarding workflow) whose side effects depend on the arguments (CSV data). While onboarding workflows typically create and activate users (Write/Execute), the tool explicitly runs a 'complete' workflow as an atomic operation, meaning the agent cannot directly control or reverse individual steps.

From the tool's definition 'Run a complete onboarding workflow for multiple users from CSV data' — this tool executes an external operation (onboarding workflow) with effects determined by the CSV input provided by the agent.

Documented attack patterns abuse exactly the kind of access run_onboarding_workflow gives an agent:

POLICY

How to control run_onboarding_workflow

PolicyLayer is an MCP gateway — it sits between your AI agents and Okta MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_onboarding_workflow:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_onboarding_workflow": {
      "limits": [
        {
          "counter": "run_onboarding_workflow_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_onboarding_workflow 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.

Create a free account and register Okta MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Okta MCP Server tools

Destructive delete_group Delete a group from Okta Destructive delete_user Delete a user from Okta (must be deactivated first) Destructive deactivate_user Deactivate a user in Okta Destructive suspend_user Suspend a user in Okta Write remove_user_from_group Remove a user from a group in Okta Write provision_applications Provision application access for multiple users Write unsuspend_user Unsuspend a user in Okta Write activate_user Activate a user in Okta

All 21 Okta MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Okta MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_onboarding_workflow

What does the run_onboarding_workflow tool do? +

Run a complete onboarding workflow for multiple users from CSV data. It is categorised as a Execute tool in the Okta MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_onboarding_workflow? +

Register the Okta MCP Server MCP server in PolicyLayer and add a rule for run_onboarding_workflow: 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 Okta MCP Server. Nothing to install.

What risk level is run_onboarding_workflow? +

run_onboarding_workflow is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_onboarding_workflow? +

Yes. Add a rate_limit block to the run_onboarding_workflow 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.

How do I block run_onboarding_workflow completely? +

Set action: deny in the PolicyLayer policy for run_onboarding_workflow. 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.

What MCP server provides run_onboarding_workflow? +

run_onboarding_workflow is provided by the Okta MCP Server MCP server (kapilduraphe/okta-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Okta MCP Server tool call.

Start from Okta MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →