How to Use the Kandji MCP in LlamaIndex

Q: Can LlamaIndex help me understand my Kandji security policies?

Yes. Index the data from listparameters and listblueprints. This lets you query your security settings in plain English, for example, "summarize the password requirements for the 'Developers' blueprint."

Q: What's a good use case for indexing Kandji user data with LlamaIndex?

Ingest listusers and listdevices to build a queryable directory. Then you can ask "what devices are assigned to john.doe@example.com?" and get an immediate, accurate answer from your indexed data.

Q: Does this MCP Server let me see which apps are deployed?

It does. Your LlamaIndex application can call listautoapps and listcustomapps, then index the results. This gives you a searchable catalog of all software managed by Kandji across your fleet.

Index your Kandji MDM data and build RAG apps that know your Apple fleet with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Kandji to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Searchable Device Inventory

Stop guessing about your device state. Use LlamaIndex to run `list_devices` and `get_device` on a schedule, then index the output into a vector store. Now you can ask natural language questions about your fleet. For example, query "show me all MacBooks with an outdated OS" or "which devices are assigned to the engineering blueprint?". LlamaIndex finds the answer from the indexed Kandji data, not a generic model, so the response is grounded in reality. This MCP server feeds the index.

Query Historical Device Activity with LlamaIndex

Your agent can create a living audit log. By using this MCP server to periodically call `list_activity` and `list_commands`, you can index every single management action taken in Kandji. Nothing gets lost. This means you can ask questions like "what commands were sent to device ID 12345 in the last week?" or "who initiated the last OS update?". Your app searches the indexed history and gives you a specific, time-stamped answer.

Ground Security Audits in Real Data

Build a RAG application that knows your security posture. Index the output of `list_parameters`, `list_blueprints`, and `list_auto_apps`. This creates a knowledge base of your security policies and software library. When you ask "is FileVault enabled on production blueprints?", your LlamaIndex app can retrieve the relevant policy from the index via `list_parameters`. It can then cross-reference it with device data from `list_devices` to give you a precise, verifiable answer.

Setup guide

Set up Kandji MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Kandji MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Kandji tools.",
)
response = await agent.run("List recent Kandji data")

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 LlamaIndex

You use LlamaIndex and this MCP server to ingest the output of Kandji tools like `list_devices`. Once indexed, you can ask your RAG application questions like "how many devices are running the latest OS?" and get answers based on that data.

Yes. Index the data from `list_parameters` and `list_blueprints`. This lets you query your security settings in plain English, for example, "summarize the password requirements for the 'Developers' blueprint."

Ingest `list_users` and `list_devices` to build a queryable directory. Then you can ask "what devices are assigned to john.doe@example.com?" and get an immediate, accurate answer from your indexed data.

It does. Your LlamaIndex application can call `list_auto_apps` and `list_custom_apps`, then index the results. This gives you a searchable catalog of all software managed by Kandji across your fleet.

The server only touches your Kandji device and policy metadata. It's all processed within a V8 Isolate sandbox, which is destroyed after each operation. Your connection is secured via a single Vinkius token, keeping your Kandji API keys private.

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