How to Use the Uscreen MCP in Pydantic AI

Q: Can I use Uscreen with Pydantic AI for content listing?

Yes. When calling listcontent or getcollection, Pydantic ensures that the returned fields are exactly what your code expects. This makes building reliable streaming logic much easier.

Q: What data types are available with Uscreen and Pydantic AI?

You get access to customer details (listcustomers), product lists (listproducts), and transaction records via listtransactions. All these tools provide type-safe outputs for your Python environment.

Q: What's the best way to check API status with Uscreen and Pydantic AI?

Run checkuscreenstatus first. This validates connectivity, and because you’re using Pydantic, it also ensures that even the status response adheres to your expected data model.

Ensure correct streaming logic with Pydantic AI and Uscreen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Uscreen MCP to Pydantic AI

Create your Vinkius account to connect Uscreen 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 Uscreen with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage User Accounts

Use `get_customer` to retrieve a user's current details, ensuring the data structure matches your expected model. You can also get an overview of all users by calling `list_customers`. This guarantees that any agent action relies on validated, correct input. If the API returns junk data, Pydantic fails loudly, meaning you know immediately if your attempt to pull user info via `get_customer` was wrong.

Track Content & Media

Get media details by running `get_content`, and list all content items using `list_content`. This ensures that every piece of media your agent interacts with has a predictable structure. You can also organize them using `list_collections`. If you need to build out a specific section, use `get_collection` or check the full catalog by calling `list_collections`.

Process Sales and Memberships

Track all financial history using `list_transactions`. Since Pydantic validates every response, you know exactly what format a transaction record will take. This prevents silent errors when processing payments. To manage access levels, list subscriptions via `list_subscriptions`, or get specific membership data by running `list_subscriptions`.

Setup guide

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

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

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

The agent uses the MCP Server tools, and every response is validated against your defined Python models. This means when you call `list_products`, for example, you get data that actually fits the schema, preventing runtime errors.

Yes. When calling `list_content` or `get_collection`, Pydantic ensures that the returned fields are exactly what your code expects. This makes building reliable streaming logic much easier.

You get access to customer details (`list_customers`), product lists (`list_products`), and transaction records via `list_transactions`. All these tools provide type-safe outputs for your Python environment.

Run `check_uscreen_status` first. This validates connectivity, and because you’re using Pydantic, it also ensures that even the status response adheres to your expected data model.

The server touches customer identity data. When retrieving a record using `get_customer`, your agent receives validated user profiles, allowing you to handle account actions without needing to worry about underlying data corruption.

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