mcpField
C
Census Trade

Census Trade

Remote
pipeworx.ioBusiness & Marketing0Updated 5w ago

About Census Trade

Census Trade is an MCP server for querying US Census Bureau international trade data. It supports country- and HS-code-filtered imports and exports, trade balances, and monthly partner trends, with gateway and local stdio options.

Key features

  1. 01Search imports by country or HS code
  2. 02Search exports by country or HS code
  3. 03Check country trade balances
  4. 04View monthly partner trade trends

Use cases

  1. 01Review imports for a commodity and country
  2. 02Compare exports to trading partners
  3. 03Track monthly trade shifts with one partner

MCP support

Exposes Census Trade tools to MCP clients through a Pipeworx gateway endpoint or as a local stdio server. Gateway connections also include shared Pipeworx meta-tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/census-trade/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-census-trade

Census Trade MCP — US Census Bureau International Trade data

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

ToolDescription
census_importsSearch US import data by HS commodity code and/or country. Returns import values, quantities, and commodity details. Pass country as a plain English name (e.g. "China"). Omit hs_code for total imports from a country; omit country for all countries combined.
census_exportsSearch US export data by HS commodity code and/or country. Returns export values, quantities, and commodity details. Pass country as a plain English name (e.g. "Mexico"). Omit hs_code for total exports to a country; omit country for all countries combined.
census_trade_balanceCheck US trade balance with a specific country for a given year. Returns net trade value and breakdown by end-use commodity category.
census_trade_trendsMonthly US trade trends with ONE trading partner — month-by-month imports and exports for a country, optionally narrowed to an HS commodity, to show seasonality and shifts. A country is required: an unfiltered monthly query spans every partner and the Census API cannot return it in time. For all-countries totals use census_imports / census_exports instead.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "census-trade": {
      "url": "https://gateway.pipeworx.io/census-trade/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/census-trade/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/census_imports \
  -H 'Content-Type: application/json' \
  -d '{"country":"European Union","hs_code":"30","year":"2024"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/census_imports. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "census-trade": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-census-trade"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-census-trade

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Census Trade data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.