How to Use the Kandji MCP in AutoGen

Q: How do AutoGen agents use Kandji data to make decisions together?

One agent might use listdevices from the Kandji MCP server to flag a vulnerable device. Another agent can then use listusers to identify the owner and discuss the best way to notify them before taking action.

Q: Can I create an AutoGen team to audit Kandji security settings?

Yes. Assign one agent to get policies with listparameters and another to check deployed apps with listautoapps. They can then compare notes and report any conflicts between policy and reality.

Q: How can my agents see what device configurations are available?

Your agents can call listblueprints to get a complete list of all device configuration profiles in Kandji. This is the starting point for any agent conversation about assigning devices to the correct groups.

Use AutoGen agent teams to debate and decide on Kandji MDM policies for your Apple fleet.

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 AutoGen

Create your Vinkius account to connect Kandji to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Security Policies with AutoGen

Set up two agents to argue about update policies. A "SecurityAgent" can use `list_devices` to find devices with old OS versions and demand an immediate update. It uses data to make its case. A "ProductivityAgent" can counter by using `list_custom_apps` to argue that a forced update might break critical developer tools. They'll debate, using Kandji data from this MCP server as evidence, until they reach a consensus on a rollout plan.

Let Agents Manage a Staged Rollout

Create a "PlannerAgent" that designs a phased deployment. It uses `list_blueprints` to identify pilot and production groups. Then, it uses `list_users` to see who is in each group. An "ExecutorAgent" then takes the plan and monitors the rollout using this MCP server to check `list_activity` for progress and `list_commands` to verify actions. If the Planner and Executor disagree on the status, they can discuss and resolve it.

Automate Collaborative Incident Response

When a device is reported lost, an "InvestigatorAgent" can be triggered. It uses `get_device` to pull the asset's last known IP and status, and `list_users` to identify the owner. It presents its findings to a "DecisionAgent". The DecisionAgent can then debate whether to issue a remote lock or wipe command via the MCP server. This multi-agent check prevents accidental wipes and creates an audit trail of the decision.

Setup guide

Set up Kandji MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kandji tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kandji_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kandji data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kandji_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kandji data")
    print(result.messages[-1].content)

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 AutoGen

One agent might use `list_devices` from the Kandji MCP server to flag a vulnerable device. Another agent can then use `list_users` to identify the owner and discuss the best way to notify them before taking action.

Yes. Assign one agent to get policies with `list_parameters` and another to check deployed apps with `list_auto_apps`. They can then compare notes and report any conflicts between policy and reality.

A security agent might propose wiping a device. A support agent could counter by checking `list_activity` and arguing the device was recently online, suggesting a `lock` command is a better first step.

Your agents can call `list_blueprints` to get a complete list of all device configuration profiles in Kandji. This is the starting point for any agent conversation about assigning devices to the correct groups.

Yes. The server only processes Kandji metadata about your devices, users, and policies. Each request runs in an ephemeral, sandboxed environment on Vinkius, and your auth token encrypts the connection. Your core Kandji credentials are not used.

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