How to Use the NAICS/SIC Classification API MCP in Google ADK

Q: Is there a way to check if the NAICS/SIC Classification API is working before my Google ADK agent starts a big job?

Yes, have your agent call checkapistatus first. This tool confirms the service is online and reports the database version. It's a quick, simple check to prevent your agent from starting a large batch process that's destined to fail.

Enrich your BigQuery data with official industry codes using Google ADK. Your Gemini agent can now classify records at scale.

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 Google ADK

Create your Vinkius account to connect NAICS/SIC Classification API to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect BigQuery to Industry Taxonomies

Your agent can now act directly on your Google Cloud data. Give it a task to enrich a customer table in BigQuery, and it will use the `search_naics_codes` tool to find the correct industry code for each row. The results can be written right back to a new column. Because Gemini models support long-context reasoning, your agent can process thousands of company descriptions in a single prompt. It can pull a massive batch of records, determine the right queries for the `get_classification_details` tool, and execute them efficiently. This is how you clean up an entire dataset in one go.

Classify Records with Google ADK

This MCP server exposes four simple tools your agent can call. Need to find a modern NAICS code? It uses `search_naics_codes`. Working with legacy data from an acquisition? It switches to `search_sic_codes`. It’s all handled through natural language prompts. This isn't just about search. Your agent can perform validation tasks. For example, it can cross-reference an existing SIC code in your database by fetching its details with `get_classification_details` and comparing it to the description you have on file. This is perfect for automated data integrity checks.

Filter Tools for Specific Agent Tasks

You have full control over what your agent can do. When you initialize the `McpToolset`, you can pass an optional `tool_names` filter to expose only a subset of the available tools. For an agent focused solely on data migration, you might only allow `search_sic_codes`. This lets you build specialized agents that are safer and more predictable. An agent designed for auditing won't accidentally try to perform a data cleanup task if it doesn't have access to the right tools. It's a simple way to enforce separation of duties at the agent level.

Setup guide

Set up NAICS/SIC Classification API MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with NAICS/SIC Classification API tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="NAICS/SIC Classification API_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NAICS/SIC Classification API tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You instruct the agent to read rows from your BigQuery table. For each row, it will use the company's text description as a query for the `search_naics_codes` tool. The agent can then execute a SQL statement to update the table with the returned code.

Yes, have your agent call `check_api_status` first. This tool confirms the service is online and reports the database version. It's a quick, simple check to prevent your agent from starting a large batch process that's destined to fail.

Not directly, but your agent can orchestrate it. It can use `get_classification_details` on a legacy SIC code to get its text description, then use that description as a query for the `search_naics_codes` tool to find the modern equivalent. This is a common workflow for data modernization projects.

Yes. Since Google ADK is part of the Vertex AI ecosystem, your agent can combine these MCP tools with any other cloud service. For instance, it could get a classification code and then trigger a Cloud Function or publish a Pub/Sub message.

The queries, which contain company text descriptions, are sent to the MCP server for processing. Vinkius isolates each request in a dedicated sandbox that is destroyed immediately after your response is sent. Your data is never mixed with other users' data or persisted.

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