USITC DataWeb MCP for AI. Pull official U.S. international trade flows.

Q: How do I find the correct country code for a trade query?

You can use the listmetadatavalues tool. Provide the table ID (e.g., 'imports') and the field ID for countries to see a full list of valid USITC country codes.

Q: Can I see what data tables are available before querying?

Yes, use the listmetadatatables tool to retrieve a list of all available data tables and their identifiers from the USITC DataWeb API.

Q: Before running querytradedata, what is the best way to validate country or commodity codes?

Use the listmetadatavalues tool. This function provides a list of valid values for any given field in a table, helping you avoid query failures caused by bad inputs.

Q: Which tool should I use to view the exact data points available for an export record?

Use listmetadatafields. This function returns all usable field names—like 'commodity' or 'customsvalue'—for a specific table you want to analyze. It shows what metrics are actually trackable.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

USITC DataWeb connects your AI client to official U.S. international trade data. Query import/export statistics, trade balances, and commodity values using recognized classification codes like HS, SITC, or NAICS.

It lets you pull complex economic records—from country-level totals down to specific product categories—without needing manual database joins or CSV downloads.

What your AI can do

List metadata fields

Shows a list of all columns available in a specific data table so you know what fields to query.

List metadata tables

Retrieves the names of every core dataset (table) hosted on the USITC DataWeb server.

List metadata values

Lists all valid entries for a filter field, like country codes or specific commodity levels, ensuring your data is accurate.

+ 1 more capabilities included

List available data tables

Find out what core datasets (like 'imports' or 'exports') exist in the USITC repository using list_metadata_tables.

Inspect table fields

Check which specific columns and data points are available within a chosen dataset by calling list_metadata_fields.

Validate input values

Confirm valid entries for categorical filters, such as official country codes or commodity levels, using list_metadata_values.

Query trade statistics

Run the main query to retrieve specific trade volumes and values using query_trade_data, filtering by classification code (HS/SITC/NAICS), country, and time period.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

USITC DataWeb (International Trade Commission): 4 Tools for Global Trade Analysis

Use these four tools to list metadata, validate inputs, and run complex queries on U.S. international trade statistics.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using USITC DataWeb (International Trade Commission) on Vinkius

List Metadata Fields

Shows a list of all columns available in a specific data table so you know what fields to query.

List Metadata Tables

Retrieves the names of every core dataset (table) hosted on the USITC DataWeb server.

List Metadata Values

Lists all valid entries for a filter field, like country codes or specific commodity...

Query Trade Data

Runs the main query to pull detailed US trade statistics based on filters like HS...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The USITC DataWeb integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "usitc-dataweb-international-trade-commission": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the USITC DataWeb tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"usitc-dataweb-international-trade-commission": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with USITC DataWeb (International Trade Commission), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by USITC DataWeb. 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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 4 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Pulling trade statistics shouldn't feel like running SQL on a college campus server.

Today, getting global trade data means jumping between multiple government websites. You download a massive CSV file, then you spend an hour manually filtering by HS code and country to isolate the numbers you actually need for your report. It's click-heavy, tedious, and prone to human error.

With USITC DataWeb MCP Server, you just tell your agent what you want—like 'trade balance for semiconductors from Japan in 2018.' The server handles all the internal API calls, metadata checks, and complex data joins. You get a clean, structured output directly into your chat window.

USITC DataWeb MCP Server: Query trade statistics with confidence.

Before this server, you had to guess which table held the right data or if a certain country code was even valid. You were constantly cross-referencing external documentation just to run a basic query, wasting hours on setup instead of analysis.

Now, the metadata tools let your agent check everything first. It verifies tables with `list_metadata_tables` and validates every country code with `list_metadata_values`. You write the prompt; it handles the guardrails.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Look, you gotta connect your agent to the USITC DataWeb server if you wanna pull official U.S. international trade numbers. This thing lets you run detailed queries on global imports, exports, and total trade balances—no messing around with manual data joins or downloading massive CSV files. It's all about querying structured government records directly through simple instructions.

You don't gotta know the underlying API structure; your AI client handles all that heavy lifting.

When you start out, the first thing you need to do is figure out what datasets are even available. You use list_metadata_tables to get a list of every core dataset—every table in the USITC repository. This tells you if they got 'imports' or maybe 'exports' listed right there so you know where to start looking.

Once you pinpoint the right dataset, you gotta inspect it. You call list_metadata_fields to check which specific columns and data points are available within that chosen table. It shows you exactly what fields exist—which is crucial because different tables store different kinds of numbers, like raw commodity volumes versus dollar values.

Before you run the main query, you need to validate your inputs. You use list_metadata_values to confirm valid entries for any filter field you plan on using. Need to filter by country? This tool shows you the official country codes so you don't accidentally send bad data. It works the same way for specific commodity levels or other categorical filters, keeping sure your query is airtight.

Finally, when you're ready, you run query_trade_data. You pass along all those validated parameters—the HS code, the country filter, the time period—and it pulls the detailed US trade statistics. This tool runs the main query to retrieve specific trade volumes and values using complex filters like classification codes (HS/SITC/NAICS), a specified country, and a date range.

It's designed for anyone who needs reliable, official numbers without building out complicated SQL queries or wrestling with messy data formats. You can get everything from broad country-level totals down to specific product categories using the classification codes. The system supports large filter sets via POST requests, meaning you can load up your query parameters and it handles them.

It's straightforward: find the table, check the columns, validate your inputs, then run the main query. That’s how you pull accurate trade data.

Built · Hosted · Managed by Vinkius USITC DataWeb MCP Server - Query Trade & Import Export Data

Server ID 019e3905-4989-70ba-bdf7-a5d56d280934

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is: You ask your agent a question about global trade, and it uses these tools to pull official data without you writing any API calls yourself.

Subscribe to the server and provide your USITC DataWeb API Key.

Use list_metadata_tables or list_metadata_fields to scope out exactly what data is available for your query.

Invoke query_trade_data, passing the specific filters (e.g., commodity code, country) and time frame you need.

Who is this actually for?

This server is for analysts who deal with international commerce. It's the economist who needs to compare commodity price fluctuations across continents over decades, or the policy researcher who has to audit historical trade balances against government standards. If your job involves cross-border goods and numbers, you need this.

International Trade Analyst

Runs reports comparing export values for specific commodity codes across different years using query_trade_data.

Supply Chain Manager

Monitors real-time trade flow patterns and tracks changes in tariffs or commodity movements by checking data from the USITC DataWeb.

Economic Policy Researcher

Audits historical trade balances and verifies official government statistics to support policy white papers, using metadata tools first for validation.

What Changes When You Connect

You get immediate access to full trade volumes and values for specific sectors. Instead of downloading massive CSV files, your agent uses query_trade_data to deliver the precise data points you need right in your workspace.

Stop guessing which columns exist. Use list_metadata_fields first. It shows exactly what data a table contains—commodity, country, year—so you build your queries with confidence.

Never worry about invalid filters again. Before querying, use list_metadata_values to get the official list of valid country codes or commodity classifications for that specific dataset.

Analyze trends over time easily. Run historical comparisons by specifying a date range in query_trade_data. You can compare trade data from 2010 vs. 2022, instantly.

Work with multiple classification standards simultaneously. The server supports querying using Harmonized Tariff Schedule (HS), SITC, or NAICS codes, making your analysis comprehensive.

See it in action

01 01

Comparing commodity shifts over a decade

A researcher needs to see how the trade volume for electronics changed from 2010 to 2020. They ask their agent, which first uses list_metadata_tables to find the 'exports' table. Then it uses query_trade_data, filtering by the commodity code and specifying a decade-long date range. The result is a clean, time-series data set.

02 02

Verifying country codes before querying

A supply chain analyst wants to check trade between Vietnam and India. They first use list_metadata_values on the 'country' field to confirm both nations have active, correct codes for that specific data table. Once validated, they run query_trade_data knowing their inputs are official.

03 03

Auditing a tariff change

A policy researcher needs data on textiles using the HS code system. They use the metadata tools to confirm the correct table and fields, then run query_trade_data for a specific period (e.g., before/after a policy date). This process provides audited numbers directly from the government source.

04 04

Finding out what data is available

A new analyst lands on the server and doesn't know where to start. They simply call list_metadata_tables, which returns 'imports', 'exports', and 'balance'. This immediately narrows their focus and tells them exactly which datasets they need for their task.

The honest tradeoffs

Assuming field names

Anti-pattern

Trying to run query_trade_data by guessing the column name is 'product type' when the actual field is 'commodity'. The query fails because of an unknown parameter.

The Fix

Always start with list_metadata_fields on the target table. This shows you the exact, required technical names (e.g., 'commodity') to use in your filters and queries.

Mixing up data types

Anti-pattern

Running a query that requires country codes but accidentally passing a commodity code instead. The system rejects the request because the input type is wrong.

The Fix

Use list_metadata_values for any filter that relies on categorical inputs (like country or classification). It validates the acceptable list of values before you commit to the query.

Overlooking table structure

Anti-pattern

Trying to run a detailed trade balance report using the 'imports' dataset. The fields won't match, and the resulting data will be incomplete or nonsensical.

The Fix

Start by calling list_metadata_tables. This forces you to select the correct primary dataset ('balance', 'imports', etc.) before trying any specific query.

When It Fits, When It Doesn't

Use this server if your job requires accessing official, structured U.S. government data on international trade (exports, imports, tariffs). It's ideal when you need to run complex queries combining multiple filters: commodity code AND country AND time period.

Don't use it if you only need simple calculations based on a single uploaded spreadsheet, or if your required data is non-standardized (e.g., internal company metrics). For those cases, a local file processing tool will work better. If you just want to know what data exists before querying, treat the metadata tools (list_metadata_tables, etc.) as your first step—they are essential scaffolding for using query_trade_data correctly.

Questions you might have

How do I find the correct country code for a trade query? +

You can use the list_metadata_values tool. Provide the table ID (e.g., 'imports') and the field ID for countries to see a full list of valid USITC country codes.

What classification systems are supported for commodity queries? +

The server supports 'hs' (Harmonized System), 'sitc' (Standard International Trade Classification), and 'naics' (North American Industry Classification System) via the query_trade_data tool.

Can I see what data tables are available before querying? +

Yes, use the list_metadata_tables tool to retrieve a list of all available data tables and their identifiers from the USITC DataWeb API.

What credentials are required to run `query_trade_data` on USITC DataWeb? +

You must provide a valid API Key. The server requires you to supply your specific USITC DataWeb API Key during the setup process to authorize all data retrievals.

Before running `query_trade_data`, what is the best way to validate country or commodity codes? +

Use the list_metadata_values tool. This function provides a list of valid values for any given field in a table, helping you avoid query failures caused by bad inputs.

Which tool should I use to view the exact data points available for an export record? +

Use list_metadata_fields. This function returns all usable field names—like 'commodity' or 'customs_value'—for a specific table you want to analyze. It shows what metrics are actually trackable.

How does the USITC DataWeb handle very large or complex filter sets when I run `query_trade_data`? +

The tool uses a POST method, which is designed to support large filter sets. This mechanism lets you send and process complicated queries with many criteria without hitting limitations.

Does `query_trade_data` support granular time-series analysis, like monthly reports? +

Yes, the tool handles both annual and monthly granularity. You simply need to specify the desired time period (year/month) in your query parameters when you call the function.

Connect to your AI in seconds.

List metadata fields

List metadata tables

List metadata values

USITC DataWeb (International Trade Commission): 4 Tools for Global Trade Analysis

Make your AI actually useful.

List Metadata Fields

List Metadata Tables

List Metadata Values

Query Trade Data

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Pulling trade statistics shouldn't feel like running SQL on a college campus server.

USITC DataWeb MCP Server: Query trade statistics with confidence.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Comparing commodity shifts over a decade

Verifying country codes before querying

Auditing a tariff change

Finding out what data is available

The honest tradeoffs

Assuming field names

Mixing up data types

Overlooking table structure

When It Fits, When It Doesn't

Questions you might have