How to Use the Wing Assistant MCP in Pydantic AI

Q: How do I check the status of a task using Wing Assistant and Pydantic AI?

You call gettaskstatus. Because it's running through Pydantic validation, you never get corrupted or hallucinated status data—it’s always clean.

Q: What is the best way to list all available assistants with Wing Assistant and Pydantic AI?

The listassistants tool gives you a complete, validated list of every virtual assistant. If the data doesn't match the schema, it won't show up.

Q: Does the Pydantic AI framework guarantee correct task updates for Wing Assistant?

Yes. When you run updatetask, Pydantic ensures that every field you send matches the required structure, preventing silent failures and data corruption.

Q: Is this server model-agnostic?

It is. Since it uses a unified approach via MCPToolset, your agent doesn't care if the underlying LLM is OpenAI, Anthropic, or local—it just focuses on structured data exchange.

Manage workflows by delegating tasks to virtual assistants with guaranteed data correctness using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wing Assistant MCP to Pydantic AI

Create your Vinkius account to connect Wing Assistant 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 Wing Assistant with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create and modify unit of work

The `create_task` tool lets your agent spin up a new, defined piece of work. It requires you to pass a title and description, which are then validated against Pydantic models. You can also change things using `update_task`. This function reliably modifies existing task records; the data must match expected types or the call fails loudly.

Monitor status across all units

Get a current unit of work status with `get_task_status` and list every assigned item via `list_tasks`. These calls ensure you get structured, predictable data back. You can also see exactly which assistants are active by calling `list_assistants`, getting verified details on your entire roster.

Handle assistant discovery

The `get_assistant` tool pulls all the specific, type-safe details for a single named virtual helper. You get exactly what you asked for, guaranteed. For an overall view of your system's resources, use `list_assistants` to see every available assistant.

Setup guide

Set up Wing Assistant 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": {
        "wing-assistant-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You call `get_task_status`. Because it's running through Pydantic validation, you never get corrupted or hallucinated status data—it’s always clean.

The `list_assistants` tool gives you a complete, validated list of every virtual assistant. If the data doesn't match the schema, it won't show up.

Yes. When you run `update_task`, Pydantic ensures that every field you send matches the required structure, preventing silent failures and data corruption.

It is. Since it uses a unified approach via `MCPToolset`, your agent doesn't care if the underlying LLM is OpenAI, Anthropic, or local—it just focuses on structured data exchange.

The server manages task definitions and status. The data types involved are Task Titles, Descriptions, and current Status metadata.

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