How to Use the AirOps MCP in Pydantic AI

Q: How do I set up the AirOps MCP server with Pydantic AI?

First, pip install "pydantic-ai-slimmcp". Then, create an MCPToolset instance with your Vinkius server URL. You pass that instance into the toolsets list when you initialize your Pydantic AI agent.

Get type-safe, validated control over AirOps workflows directly in Python with Pydantic AI. Correctness you can count on.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirOps MCP to Pydantic AI

Create your Vinkius account to connect AirOps 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 AirOps with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Workflow Execution

This server lets your agent run AirOps jobs using `execute_workflow_sync` for immediate results or `execute_workflow_async` for tasks that can run in the background. Pydantic AI automatically parses and validates every response against a Pydantic model. If AirOps returns data in an unexpected format, your code raises a `ValidationError` on the spot. No silent failures, no corrupted data. Your agent can also track these jobs with `get_execution_status` and `cancel_execution`, and each of those status checks is just as rigorously validated.

Build a Structurally Sound Memory

Your agent can build out a knowledge store using `add_memory_document` and `upload_file`. The real advantage comes when your agent needs to retrieve that information. When your agent calls `search_memory_store`, the list of results is guaranteed to match your Pydantic models. This prevents the agent from hallucinating fields or misinterpreting the structure of its own memory. You're building a system that is provably correct, not just probably correct.

Manage Apps with your Pydantic AI Agent

Let your agent see exactly what it can do. The `list_apps` tool returns a list of all available AirOps applications, and Pydantic AI ensures that list is correctly formatted before your code ever touches it. From there, your agent can dig into a specific app with `get_app_details`. The response, which contains all the app's metadata, is validated instantly. This is how you build reliable, introspective agents that don't break when an upstream API changes. This MCP Server makes that simple.

Setup guide

Set up AirOps 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": {
        "airops-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent AirOps 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 AirOps. 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 AirOps 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 AirOps MCP in Pydantic AI

First, `pip install "pydantic-ai-slim[mcp]"`. Then, create an `MCPToolset` instance with your Vinkius server URL. You pass that instance into the `toolsets` list when you initialize your Pydantic AI agent.

Data integrity. Pydantic AI validates every single response from the AirOps tools against your models. If a tool like `get_app_details` returns an unexpected field, your code fails loudly and immediately, which is exactly what you want for production code.

Yes, Pydantic AI is model-agnostic. You can use it with OpenAI, Anthropic, Gemini, or a local model running on your own machine. The AirOps toolset is independent of the LLM you choose to power the agent's reasoning.

If an AirOps tool returns data that doesn't match the expected Pydantic model, Pydantic AI raises a `ValidationError`. This stops errors at the source, preventing your agent from making bad decisions based on corrupted or unexpected data.

The server processes API call contents, including workflow commands and data sent via tools like `upload_file`. All processing occurs in a sandboxed, single-use V8 Isolate on Vinkius. Your agent's operational data is not logged 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