How to Use the Uselessfacts MCP in Pydantic AI

Q: If I want a German fact using Uselessfacts with Pydantic AI, which tool do I use?

Use getrandomfact(language='de') or gettodayfact(language='de'). The framework handles the language parameter and validates the resulting string.

Guaranteed Data Types with Uselessfacts | 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 Uselessfacts MCP to Pydantic AI

Create your Vinkius account to connect Uselessfacts 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 Uselessfacts with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Fact by ID using `get_fact`

The `get_fact(id)` tool provides a specific useless fact, and the MCP Server ensures this output validates correctly against your Pydantic model. You get a reliable string back. This type-safe approach means you never have to worry about unexpected data formats corrupting your agent's state.

Retrieve Random Facts with `get_random_fact`

Calling `get_random_fact()` gives your agent a random fact, and the output is guaranteed to conform to the Pydantic schema. You control language via 'en' or 'de'. If the underlying API returns bad data, the validation fails loudly, stopping corruption before it starts.

Get Today’s Fact with `get_today_fact`

Use `get_today_fact()` to get the daily fact, specifying 'en' or 'de'. Since the response is validated at runtime, you can treat it like any other predictable piece of data. This means your agent code can trust that the field names and types are exactly what they should be.

Setup guide

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

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

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

The MCP Server ensures every response is validated against your defined Pydantic model. This prevents silent data corruption, guaranteeing that the agent receives expected fields and types.

You can chain calls using different tools—like first getting a fact by ID, then calling for a random fact. The validation layer ensures every single response is clean.

The server handles simple text strings (the facts) and IDs. Because of Pydantic, you're always dealing with predictable string types that your Python code expects.

Use `get_random_fact(language='de')` or `get_today_fact(language='de')`. The framework handles the language parameter and validates the resulting string.

Absolutely. The core benefit is that every MCP Server response, including facts from this server, must pass through your runtime validation layer. If it fails, the agent stops.

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