How to Use the Numbers API MCP in Pydantic AI

Q: How does Pydantic AI validate responses from the Numbers API?

The framework wraps tools like getmathfact and validates the returned string against your defined Pydantic models. If the response contains unexpected characters, the runtime raises a clear validation error.

Q: What happens if the upstream numbers server goes down?

If the connection fails during a getdatefact call, Pydantic AI will raise a network error. You can catch this exception in your Python code to fallback to a cached value or a default string.

Run type-safe numeric and date queries with the Numbers API and 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 Numbers API MCP to Pydantic AI

Create your Vinkius account to connect Numbers API 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 Numbers API with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Mathematical Validation

The `get_math_fact` tool delivers mathematical properties that Pydantic AI validates against strict runtime types. If the upstream service returns a malformed string, the framework raises a validation error immediately. That prevents corrupt data from entering your application logic. This strict validation ensures your agents never hallucinate mathematical properties. You get predictable, verified text responses. They match your exact schema requirements.

Validated Historical Timelines

The `get_year_fact` and `get_date_fact` tools retrieve historical data that your agent can safely parse into structured models. Pydantic AI inspects the returned text to ensure it matches the expected structure before your agent uses it for downstream tasks. This managed MCP server handles the connection details behind a single endpoint. You do not have to write custom error-handling code to catch bad API responses; the framework handles it at the boundary.

Safe Trivia Processing for Pydantic AI

The `get_trivia_fact` and `get_random_fact` tools supply general trivia that your model-agnostic agent can consume. Whether you use local models or commercial APIs, the inputs and outputs are validated at runtime to keep your execution path clean. By running this server on Vinkius, you avoid hosting overhead. Your Python code connects to the running MCP server via SSE or HTTP, maintaining type-safety across the entire network hop.

Setup guide

Set up Numbers API 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": {
        "numbers-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

The framework wraps tools like `get_math_fact` and validates the returned string against your defined Pydantic models. If the response contains unexpected characters, the runtime raises a clear validation error.

Yes, Pydantic AI is model-agnostic, allowing you to route facts from `get_trivia_fact` to local models. The framework validates the tool outputs before passing them to your local model.

Instantiate the MCP server toolset with our secure HTTP endpoint and pass it to your agent constructor. This unified approach replaces the deprecated HTTP client and registers all five tools instantly.

If the connection fails during a `get_date_fact` call, Pydantic AI will raise a network error. You can catch this exception in your Python code to fallback to a cached value or a default string.

No, our V8 sandbox processes your requested integers, years, and dates ephemerally. The data is processed in memory to fetch the fact and is completely destroyed once the response is sent back to your agent.

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