How to Use the Kandji MCP in OpenAI Agents SDK

Control your Apple fleet directly from your OpenAI Agents SDK runtime with zero-config tool discovery and built-in execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kandji MCP to OpenAI Agents SDK

Create your Vinkius account to connect Kandji to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kandji with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Apple fleets using OpenAI Agents SDK

`list_devices` fetches real-time hardware states, OS versions, and identifiers directly into your agent's context. Your agent uses this telemetry to isolate outdated endpoints or flag unassigned hardware without manual intervention. You feed this data into specialized agents that handle security triage. The agent queries `get_device` to inspect a flagged asset's specific profiles, checking compliance status before initiating remediation steps.

Verify software compliance and blueprints

`list_blueprints` exposes the exact configuration profiles assigned to your macOS and iOS hardware. Your agent parses these blueprints to verify that target devices run required security baselines. It checks standard installations via `list_auto_apps` and specialized packages using `list_custom_apps`. If a mismatch occurs, the agent triggers an alert or queues up updates using the OpenAI dashboard to trace the decision tree.

Monitor MDM command history with safety guardrails

`list_commands` retrieves the history of remote actions like locks, wipes, or restarts dispatched to your fleet. The SDK's native guardrails ensure your agent never triggers destructive actions without explicit confirmation. The agent correlates these commands with system audits by pulling recent events via `list_activity`. This keeps your security team informed of administrative changes while preventing runaway automated actions.

Setup guide

Set up Kandji MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kandji tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kandji tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kandji tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kandji Agent",
            instructions="You have access to Kandji tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kandji. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kandji now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kandji MCP in OpenAI Agents SDK

The SDK auto-discovers all ten MDM tools when you register the MCP Server streamable HTTP endpoint. Your agent inspects the schema and instantly understands how to call tools like `list_devices` or `list_blueprints` without manual mapping.

Yes, you control this by configuring Vinkius endpoint permissions or setting system guardrails inside your Python code. You can limit your agent to read-only tools like `list_users` and completely block access to tools that fetch command history.

Yes, you can route different MDM tasks to specialized agents. For example, a triage agent checks fleet health via `list_devices`, then hands off to an audit agent that queries `list_activity` to log compliance status.

Vinkius handles the authentication handshake externally. You pass a single secure endpoint token to your Python code, which connects to the hosted MCP Server without exposing your raw MDM API keys to the agent runtime.

Your macOS serials, user assignments, and installed app lists remain protected inside the Vinkius V8 Isolate Sandbox. The hosted MCP Server processes payload data in ephemeral, zero-trust environments, preventing persistent storage of your fleet's internal configuration details.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript