How to Use the airfocus MCP in Pydantic AI

Q: What's the difference between MCPServerHTTP and MCPToolset for connecting to airfocus?

MCPToolset is the modern, recommended way to connect to any MCP Server in Pydantic AI. It's a more unified interface, while the older MCPServerHTTP class is now deprecated. You should use MCPToolset for this server.

Build type-safe agents that manage your airfocus roadmap. Pydantic AI validates every response so your data stays clean.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect airfocus MCP to Pydantic AI

Create your Vinkius account to connect airfocus 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 airfocus with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Update airfocus with Confidence

Your agent can manage the full lifecycle of a product idea. It can propose a new feature with `create_airfocus_item`, check its details later with `get_airfocus_item`, and modify it with `update_airfocus_item`. It's a direct, programmable interface to your roadmap. Here’s the Pydantic AI advantage: every response from the server is automatically parsed and validated. If your agent calls `get_airfocus_item` and the airfocus API returns an unexpected data structure, your code will raise a `ValidationError` instantly. No silent failures, no corrupted data.

Query Your Workspace, Your Way

Give your agent the tools to understand your product strategy. It can `list_airfocus_workspaces` to get a high-level view, then drill down into a specific backlog with `list_airfocus_items`. It can even check what custom fields are available with `list_airfocus_fields` before trying to create a new item. Because Pydantic AI is model-agnostic, you can pair these tools with any LLM you want—OpenAI, Anthropic, or a local model running on your machine. The Pydantic validation layer works the same no matter what. It guarantees that the airfocus data your agent works with is always correctly structured.

Connect Pydantic AI to Your MCP Server

The setup is exactly what you'd expect: simple. You instantiate an `MCPToolset` with the Vinkius URL and add it to your Pydantic AI `Agent`. The framework handles the tool discovery and invocation for you. This approach is all about correctness. By using this MCP Server, you're ensuring that every tool call to airfocus and every response that comes back is type-checked. You spend less time debugging strange API behavior and more time building reliable agent logic.

Setup guide

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

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

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

Pydantic AI automatically validates every JSON response from the server against a Pydantic model. If the data doesn't match the expected schema—for example, a field is missing or has the wrong type—it raises a `ValidationError` so you can handle the error immediately.

Yes. Pydantic AI is model-agnostic. You can configure it to use any LLM, including local models like Llama or Mistral, and the `MCPToolset` for airfocus will work exactly the same way.

By default, Pydantic will simply ignore the extra field during validation, which prevents your agent from crashing. If you need stricter behavior, you can configure the underlying Pydantic model to forbid extra fields, which would cause a `ValidationError`.

`MCPToolset` is the modern, recommended way to connect to any MCP Server in Pydantic AI. It's a more unified interface, while the older `MCPServerHTTP` class is now deprecated. You should use `MCPToolset` for this server.

The server is designed to work with your airfocus items, workspaces, and custom fields. Vinkius secures the connection by handling all authentication; your application only needs a single, revokable API token. All processing happens in a sandboxed V8 Isolate, ensuring your data is never co-mingled or exposed.

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