How to Use the Smarty MCP in Pydantic AI

Q: How does Smarty help my Pydantic AI process US addresses?

When using validateusaddress, the MCP Server returns data that must match your Pydantic model. If the tool outputs unexpected fields, your agent fails validation immediately. This prevents bad address data from entering your database.

Q: What happens if Smarty finds an international address using my Pydantic AI?

The validateintladdress output is automatically checked against your schema. It validates and geocodes the global address, and because of Pydantic's guardrails, you know exactly which fields are present and what type they are.

Q: Can Smarty find addresses in documents using my Pydantic AI?

Absolutely. Your agent runs extractaddresses on the document text. The tool finds physical addresses, but Pydantic ensures that this extracted data is correctly typed and structured before you use it.

Q: What account details does Smarty provide my Pydantic AI?

The agent calls getaccountinfo to get user or system context. This information is returned, and Pydantic validates that the fields (like user ID or status) are exactly what your model expects.

Ensure perfect data structure: Use Smarty's MCP Server with Pydantic AI validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Smarty MCP to Pydantic AI

Create your Vinkius account to connect Smarty to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Smarty with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate US addresses for correctness

The `validate_us_address` tool validates a US street address and returns its Delivery Point Validation (DPV) status. Because your agent uses Pydantic, it forces the output to conform to expected schemas—no silent data corruption. This means if the API response structure is unexpected, the whole process fails loudly with a validation error, keeping your system safe.

Standardize international addresses

When dealing with global inputs, use `validate_intl_address`. It validates and geocodes an international street address based on the required line and country. Pydantic ensures that even complex foreign data fits into your defined Python models. This reliability is key when you can't afford to hallucinate fields from external location services.

Extract addresses for clean schemas

Raw text often messes up structured data. The `extract_addresses` function pulls physical addresses out of documents or emails, alongside other types like phone numbers and URLs. This raw extraction is then validated by Pydantic. You get a guaranteed structure: the address string plus its type, ready to map directly into your models.

Setup guide

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

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

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

When using `validate_us_address`, the MCP Server returns data that must match your Pydantic model. If the tool outputs unexpected fields, your agent fails validation immediately. This prevents bad address data from entering your database.

The `validate_intl_address` output is automatically checked against your schema. It validates and geocodes the global address, and because of Pydantic's guardrails, you know exactly which fields are present and what type they are.

Absolutely. Your agent runs `extract_addresses` on the document text. The tool finds physical addresses, but Pydantic ensures that this extracted data is correctly typed and structured before you use it.

The agent calls `get_account_info` to get user or system context. This information is returned, and Pydantic validates that the fields (like user ID or status) are exactly what your model expects.

The server handles physical address information across multiple formats. Since you're using Pydantic, all returned location intelligence—US addresses, international addresses, and extracted text—will be validated against defined Python classes.

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