How to Use the Kandji MCP in LangChain

Q: How does LangChain use Kandji tools for multi-step device checks?

LangChain agents use tools sequentially. An agent can call listdevices from this MCP server to get a list of Macs, then call getdevice on each one to check its OS version, creating a full compliance report in one run.

Q: Can I build a LangChain agent to find unapproved software with Kandji?

Yes. Your agent can call listcustomapps to get a list of all non-standard apps. It can then compare that against an approved list to flag any unauthorized software on your managed devices.

Q: What's the best way to monitor Kandji admin actions using LangChain?

Create a monitoring agent that periodically calls listactivity and listcommands. It can then summarize recent changes, like new blueprint assignments or remote lock commands, and send you a digest.

Q: Can my agent see the overall status of my Kandji organization?

Absolutely. The getorganization tool is perfect for this. Your agent can call it to confirm the Kandji tenant details and ensure it's connected to the right account before running other commands.

Build agents that manage your entire Apple fleet with Kandji and LangChain.

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 LangChain

Create your Vinkius account to connect Kandji to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Device Audits

Create chains that check device compliance. Start with `list_devices` to get your whole fleet, then loop through each device ID, passing it to `get_device` for a detailed report. It's a simple, powerful way to build custom reports without a UI. Your agent decides what to check next. If a device from `get_device` has an old OS version, the chain can check its assigned policies using `list_blueprints`. This lets you build logic that finds and flags non-compliant machines automatically, all within a single LangChain execution.

Chain Security Policies with this MCP Server

Connect Kandji security tools in a sequence. Have your LangChain agent pull all security settings with `list_parameters`, then check which software is actually installed using `list_auto_apps` and `list_custom_apps`. The agent can spot discrepancies between policy and what's really running. You can also trace remote actions. Use `list_commands` to see what changes were pushed, then cross-reference with `list_activity` to see the results. It's all visible in LangSmith, so you can see exactly what your agent did, step-by-step.

Map Users to Hardware Assets

Build a simple chain to connect people to hardware. First, call `list_users` to get a complete list of everyone in your Kandji instance. This gives you the starting point for any user-based audit. Then, your agent can take that user list and query `list_devices` to find which assets they're assigned to. This is great for automating offboarding checklists or just figuring out who has what without digging through a web portal.

Setup guide

Set up Kandji MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kandji tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kandji-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kandji transactions"
    })
    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 LangChain

LangChain agents use tools sequentially. An agent can call `list_devices` from this MCP server to get a list of Macs, then call `get_device` on each one to check its OS version, creating a full compliance report in one run.

Yes. Your agent can call `list_custom_apps` to get a list of all non-standard apps. It can then compare that against an approved list to flag any unauthorized software on your managed devices.

Create a monitoring agent that periodically calls `list_activity` and `list_commands`. It can then summarize recent changes, like new blueprint assignments or remote lock commands, and send you a digest.

Absolutely. The `get_organization` tool is perfect for this. Your agent can call it to confirm the Kandji tenant details and ensure it's connected to the right account before running other commands.

This server processes your Kandji device, user, and policy metadata. Your Vinkius endpoint token secures the connection, and all operations happen in an isolated sandbox, so your credentials are never exposed.

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