How do I get Kandji API credentials?

Log in to your Kandji account, navigate to Settings > Access > API Token, and generate a new token. You also need your tenant's API URL.

The API URL is specific to your Kandji instance (e.g., https://yourtenant.api.kandji.io). You can find this in your Kandji API settings.

Can I see remote commands?

Yes, the list_commands tool allows you to retrieve a history of MDM commands sent to your managed devices.

Kandji MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Kandji
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Kandji through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Kandji "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Kandji?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Kandji MCP Server

Empower your AI agents with Kandji's modern Apple MDM platform. This MCP server allows you to list and retrieve device details, manage blueprints and custom apps, track administrative activity, and view system security parameters directly through the Kandji API. Ideal for automating IT operations and fleet security for macOS and iOS.

Pydantic AI validates every Kandji tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

The Kandji MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Kandji to Pydantic AI via MCP

Follow these steps to integrate the Kandji MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Kandji with type-safe schemas

Why Use Pydantic AI with the Kandji MCP Server

Pydantic AI provides unique advantages when paired with Kandji through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Kandji integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Kandji connection logic from agent behavior for testable, maintainable code

Kandji + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Kandji MCP Server delivers measurable value.

Type-safe data pipelines: query Kandji with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Kandji tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Kandji and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Kandji responses and write comprehensive agent tests

Kandji MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Kandji to Pydantic AI via MCP:

get_device

Essential for deep-dive auditing of a specific asset. Retrieves details for a specific device

get_organization

Use to verify account identity. Retrieves details about your Kandji organization

list_activity

Essential for auditing system changes and recent management history. Lists recent management activity

list_auto_apps

Essential for auditing standard software libraries. Lists all Kandji Auto Apps

list_blueprints

Useful for understanding how devices are categorized and configured. Lists all device blueprints

list_commands

g., Lock, Wipe, Restart) sent to managed devices. Useful for auditing remote actions. Lists recent MDM commands sent to devices

list_custom_apps

Useful for auditing non-store software deployments. Lists all custom applications

list_devices

Returns device names, IDs, and OS versions. Use this as the main tool for auditing the device fleet. Lists all managed Apple devices in Kandji

list_parameters

Useful for auditing available security controls. Lists all library parameters (policies)

list_users

Useful for identifying device owners and primary users. Lists all users associated with devices

Example Prompts for Kandji in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Kandji immediately.

"List all managed Mac computers in Kandji."

"Show me the details for device ID 'abc-123'."

"Check recent administrative activity in Kandji."

Troubleshooting Kandji MCP Server with Pydantic AI

Common issues when connecting Kandji to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Kandji + Pydantic AI FAQ

Common questions about integrating Kandji MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Kandji MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.