How to Use the Jservice MCP in Pydantic AI

Q: How do I add the Jservice tools to a Pydantic AI agent?

After installing pydantic-ai-slimmcp, create an MCPToolset with your Jservice endpoint URL. Pass this into the toolsets list when you initialize your Agent. The tools are then available to your agent.

Q: Can Pydantic AI agents use filters with the Jservice getclues tool?

Yes. Your agent can call the getclues tool with arguments for value, category, date, and offset. Pydantic AI ensures the arguments you pass are correctly formatted for the tool call.

Build type-safe trivia bots with Pydantic AI. Get structured, validated Jservice data in your agent, or it fails with an error. No surprises.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jservice MCP to Pydantic AI

Create your Vinkius account to connect Jservice 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 Jservice with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Validated Trivia Data

Use `get_clues` to pull Jeopardy! questions, filtering by value or date. The key is that the response is automatically parsed and validated against a Pydantic model before your agent ever sees it. No more checking for `None` or handling weirdly formatted JSON. If the Jservice API ever returns a malformed clue or an unexpected field, Pydantic AI throws a `ValidationError`. Your agent stops dead, and you know exactly what went wrong and where. This prevents data corruption from silently flowing through your system.

Structured Category and Clue Tools

The `get_categories` tool fetches a list of available trivia categories. `get_category` then pulls the details for one, including all its clues. Each tool's output is a predictable, typed object. This makes your agent logic much cleaner. You're not writing defensive code to handle missing keys or wrong data types. You just work with the Pydantic objects, confident that the data is correct because the framework already checked it for you.

Model-Agnostic Pydantic AI MCP Server

This Jservice MCP Server works out of the box with Pydantic AI. Just create an `MCPToolset` with your Vinkius server URL and add it to your agent. It doesn't matter if you're using GPT-4, Gemini, or a local Llama model. The `get_random_clues` tool is perfect for testing this. Ask your agent for a random question. The response will be validated on the fly. You get the benefit of a managed server without being locked into a specific AI provider.

Setup guide

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

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

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

After installing `pydantic-ai-slim[mcp]`, create an `MCPToolset` with your Jservice endpoint URL. Pass this into the `toolsets` list when you initialize your `Agent`. The tools are then available to your agent.

Runtime validation. Every response from the Jservice tools is automatically parsed into a Pydantic model. If the data doesn't match the expected schema, your code raises an exception immediately, preventing bad data from causing silent failures.

Yes. Your agent can call the `get_clues` tool with arguments for `value`, `category`, `date`, and `offset`. Pydantic AI ensures the arguments you pass are correctly formatted for the tool call.

Yes, and that's the point. If the API returns data that no longer matches the Pydantic models this MCP server expects, you'll get a `ValidationError`. This is a feature, as it forces you to address the change instead of letting it cause bugs.

The server only ever touches public Jeopardy! trivia data, specifically clues and categories. It has no access to your code, your models, or any user information. All communications are stateless and secured by your Vinkius API token.

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