How to Use the Kandji MCP in Google ADK

Q: How do I connect Kandji to Google ADK?

You install the library, instantiate McpToolset with the Vinkius HTTP URL to load the MCP Server, and pass it to your LlmAgent. Your Gemini-powered agent instantly gains the ability to run tools like listdevices and getdevice.

Run fleet-wide Apple device audits by linking Kandji to your Google ADK agent with Gemini long-context reasoning.

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 Google ADK

Create your Vinkius account to connect Kandji to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze fleet telemetry using Google ADK

`list_devices` extracts your entire Apple inventory, including OS versions and serial numbers, sending it straight to Gemini's million-token context window. This allows your agent to run massive comparative analysis across thousands of endpoints. The agent maps these devices to physical owners using `list_users` to pinpoint unassigned hardware. It spots patterns in fleet distribution that standard database queries miss, giving your IT team clear visibility.

Sync Google ADK telemetry with BigQuery

`list_activity` streams recent management logs directly into your Google Cloud pipelines. Your agent correlates these live MDM events with enterprise data warehouses to flag unauthorized configuration changes. It checks compliance baselines by pulling security rules from `list_parameters`. This lets you build automated reports that compare actual device states against corporate security policies in real time.

Audit application libraries via MCP Server tools

`list_custom_apps` identifies non-store software packages installed across your fleet. The agent cross-references these custom packages with threat intelligence databases inside Google Cloud. Standard software libraries are tracked separately using `list_auto_apps` to verify patch levels. This ensures your enterprise agents can verify that critical security updates are active across all active blueprints.

Setup guide

Set up Kandji MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Kandji tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Kandji_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Kandji tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You install the library, instantiate `McpToolset` with the Vinkius HTTP URL to load the MCP Server, and pass it to your `LlmAgent`. Your Gemini-powered agent instantly gains the ability to run tools like `list_devices` and `get_device`.

Yes, Gemini's long-context window lets the agent process output from `list_blueprints` and `list_parameters` simultaneously. It can evaluate security baselines across your entire company in a single reasoning loop.

Yes, you can restrict the tools exposed to the agent by using the `tool_names` filter in your Python setup. This prevents the agent from calling operational tools like `list_commands` while keeping audit tools active.

Vinkius hosts the MCP Server in a zero-trust sandbox, managing the API handshake externally. Your enterprise agent connects using a single secure token, keeping your master MDM credentials isolated from your cloud runtime.

Your fleet's serial numbers, user assignments, and application lists are processed through ephemeral V8 isolates. Vinkius never stores this MDM telemetry, ensuring your corporate asset directory remains private and isolated from external training sets.

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