How to Use the NAICS/SIC Classification API MCP in Pydantic AI

Q: What happens if the NAICS/SIC Classification API returns data that doesn't match my Pydantic AI model?

Your code will raise a ValidationError. This is the core benefit of Pydantic AI. It prevents bad data, like a missing description or an incorrectly formatted code from the getclassificationdetails tool, from ever reaching your application logic.

Q: How do I check the server's health?

The server provides a checkapistatus tool. You can have your agent call this function to verify that the service is running and get the version of the underlying NAICS/SIC dataset before starting any important tasks.

Get type-safe industry classifications for your Pydantic AI agents. Stop worrying about bad data from API calls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NAICS/SIC Classification API MCP to Pydantic AI

Create your Vinkius account to connect NAICS/SIC Classification 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 NAICS/SIC Classification API with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Validated Data Structures, Every Time

The main reason to use this server with Pydantic AI is correctness. When your agent calls `get_classification_details`, the JSON response is automatically parsed and validated against a Pydantic model. You get a clean, typed object to work with. If the API ever returns an unexpected field or a malformed code, your agent won't silently fail or pollute your database. Instead, it will raise a `ValidationError` immediately. This forces you to handle data integrity issues head-on, which is exactly what you want for financial or compliance applications.

Search NAICS/SIC with Any LLM

This MCP server gives your agent direct access to `search_naics_codes` and `search_sic_codes`. Your agent can find industry classifications based on plain text descriptions. The tools are simple, focused, and do one thing well. Pydantic AI is model-agnostic, so you can pair this server with OpenAI, Anthropic, Gemini, or a local model. The tool-calling and validation logic works the same way everywhere. You get the safety of Pydantic without being locked into a specific AI provider.

Simple and Direct Integration

There's no complex setup here. You point the `MCPToolset` to the server's URL, and Pydantic AI handles the rest. It fetches the tool definitions and makes them available to your agent. All the messy parts of function calling are abstracted away. Your agent's code becomes much cleaner. You just tell it what you want—for instance, "Find the NAICS code for 'Custom Computer Programming Services'"—and it knows to call the `search_naics_codes` tool. The framework handles the API call, the response parsing, and the validation.

Setup guide

Set up NAICS/SIC Classification 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": {
        "naicssic-classification-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NAICS/SIC Classification 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 Brand.dev. 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 NAICS/SIC Classification 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 NAICS/SIC Classification API MCP in Pydantic AI

Your code will raise a `ValidationError`. This is the core benefit of Pydantic AI. It prevents bad data, like a missing description or an incorrectly formatted code from the `get_classification_details` tool, from ever reaching your application logic.

You guide it in your prompt. If you need to find a code for a modern business, you'd instruct it to "find the NAICS code." If you're cleaning up old data, you'd tell it to "find the SIC code." The agent selects the correct tool based on your instructions.

Yes. Pydantic AI is designed to be model-agnostic. As long as your local model supports function calling, you can connect it to the `MCPToolset` and it will work just like it does with a commercial API.

The server provides a `check_api_status` tool. You can have your agent call this function to verify that the service is running and get the version of the underlying NAICS/SIC dataset before starting any important tasks.

Only the search terms, like a company description or a specific NAICS/SIC code, are transmitted. Each API call runs in a zero-trust, ephemeral environment on Vinkius. The container processing your request is terminated the moment the response is delivered, ensuring your query data isn't stored.

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