How to Use the Kandji MCP in Pydantic AI

Q: Does the Kandji integration with Pydantic AI support SSE transports?

Yes, you can connect the Pydantic AI MCPToolset to the Vinkius MCP Server using either Streamable HTTP or SSE transports. This lets you run the agent against a secure, externally hosted endpoint.

Secure your Apple fleet audits with Pydantic AI, enforcing strict type-safe validation on all Kandji MDM data at runtime.

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 Pydantic AI

Create your Vinkius account to connect Kandji to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate fleet telemetry using Pydantic AI

`list_devices` pulls hardware profiles and OS versions into your agent's runtime. The framework parses this payload against strict schemas, throwing immediate validation errors if the MDM API returns unexpected structures. This prevents silent data corruption when auditing critical assets. Your agent queries `get_device` with guaranteed type safety, ensuring fields like serial numbers and OS versions match your internal database models exactly.

Audit Kandji blueprints with runtime type checks

`list_blueprints` extracts device configurations to verify active security policies. Pydantic AI validates the structure of these blueprints before your agent can make decisions based on their contents. It checks policy configurations via `list_parameters` and verifies organization details using `get_organization`. If a policy schema changes on the MDM side, your system fails loudly, alerting your engineers before bad data spreads.

Type-check software records via MCP Server schemas

`list_custom_apps` tracks non-store application deployments across your macOS endpoints. Your agent validates these custom application records alongside standard packages retrieved via `list_auto_apps`. The agent also tracks administrative actions by querying `list_commands`. Because every response is validated against strict Pydantic models, you can safely write automated compliance pipelines without worrying about raw JSON parsing errors.

Setup guide

Set up Kandji MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "kandji-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kandji tools.",
)

result = await agent.run("List recent Kandji transactions")
print(result.output)

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 Pydantic AI

The framework uses the MCP Server schemas to generate Pydantic models at runtime. When your agent calls tools like `list_devices` or `list_users`, the incoming JSON is validated against these models, blocking malformed data instantly.

Your agent will raise a validation error immediately. This loud-failure model prevents your python code from executing logic on corrupt or unexpected payload structures, protecting your automated compliance workflows.

Yes, you can connect the Pydantic AI `MCPToolset` to the Vinkius MCP Server using either Streamable HTTP or SSE transports. This lets you run the agent against a secure, externally hosted endpoint.

Vinkius manages the authentication credentials for you. You only need to pass your Vinkius endpoint token when initializing the `MCPToolset` in your Python script, keeping your MDM keys hidden.

Your user profiles, hardware serial numbers, and installed application states are validated within your local Python runtime. Vinkius processes the data through ephemeral V8 sandboxes, ensuring your fleet telemetry is never cached or stored.

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