Can the AI find an address hidden inside a block of text automatically?

Yes! You can paste an entire email string or customer support note into your prompt and ask the AI: 'Extract any addresses mentioned in this text.' The agent triggers the `extract_addresses` engine to return the geolocated and sanitized address format purely.

How accurate is the address verification?

Smarty ensures the address is validated against official sources like the USPS using DPV (Delivery Point Validation) for US requests, guaranteeing a package can actually be delivered to the mapped coordinate. Your AI agent returns this rigorous underlying metadata.

Can I use the agent to fix my dataset dynamically without coding?

Yes. If you have 20 poorly formatted customer addresses, you can simply paste them in the prompt, asking your AI to 'Run each of these through Smarty and return a markdown table of the normalized addresses.' The agent handles the iteration loop for you via the tools.

Smarty MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Smarty through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Smarty "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Smarty?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Smarty MCP Server

Connect your Smarty account to any AI agent and empower your team to sanitize raw address data, query ZIP codes, and format global street locations securely. Interact with powerful geospatial and mailing validation APIs through natural language without writing a single line of custom script.

Pydantic AI validates every Smarty tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Address Validation (USA/Intl) — Effortlessly clean and verify messy user inputs calling validate_us_address, returning the Delivery Point Validation (DPV)
Text Extraction — Feed your AI unformatted text like emails or notes and run extract_addresses to intelligently isolate real physical addresses
Autocompletion Tests — Interrogate the AI dynamically with partial street names using the autocomplete_us_address algorithm
ZIP Code Checks — Validate specific 5-digit postal zones using verify_zip_code to retrieve associated municipal limits

The Smarty MCP Server exposes 7 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Smarty to Pydantic AI via MCP

Follow these steps to integrate the Smarty MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 7 tools from Smarty with type-safe schemas

Why Use Pydantic AI with the Smarty MCP Server

Pydantic AI provides unique advantages when paired with Smarty through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Smarty integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Smarty connection logic from agent behavior for testable, maintainable code

Smarty + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Smarty MCP Server delivers measurable value.

Type-safe data pipelines: query Smarty with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Smarty tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Smarty and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Smarty responses and write comprehensive agent tests

Smarty MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Smarty to Pydantic AI via MCP:

autocomplete_intl_address

Predictive autocomplete for international addresses

autocomplete_us_address

Predictive autocomplete for US addresses

extract_addresses

g., emails, documents) and find valid addresses. Extracts physical addresses from raw text

get_account_info

Retrieves Smarty account information

validate_intl_address

Requires at least the address line and country. Validates and geocodes an international street address

validate_us_address

Returns delivery point validation (DPV) status and coordinates. Validates and geocodes a US street address

verify_zip_code

Verifies a ZIP code and returns associated cities and states

Example Prompts for Smarty in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Smarty immediately.

"Validate this US address: 1 Santa Claus Ln, North Pole, AK 99705."

"Can you extract any known addresses from this raw text string: "I live out near the big oak tree at 1600 Amphitheatre Pkwy, Mountain View, CA 94043, come visit soon!""

"Provide a markdown list of US autocomplete suggestions when a user types "3311 w 300 s s"."

Troubleshooting Smarty MCP Server with Pydantic AI

Common issues when connecting Smarty to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Smarty + Pydantic AI FAQ

Common questions about integrating Smarty MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Smarty MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.