Skip to main content
Glama
pipeworx-io

@pipeworx/china-commerce

by pipeworx-io

@pipeworx/china-commerce

China's outward commercial activity — outward direct investment, overseas contracted engineering, overseas labour dispatch, and utilised inbound FDI — as monthly year-to-date cumulative national totals from the Ministry of Commerce's data centre.

Part of Pipeworx — an MCP gateway connecting AI agents to 1861+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

  • mofcom_odi({ start_period?, end_period?, limit? }) — non-financial outward direct investment (对外直接投资): cumulative amount (USD 100M), number of enterprises, count of countries/regions reached, and YoY %.

  • mofcom_overseas_contracting({ start_period?, end_period?, limit? }) — overseas contracted engineering (对外承包工程): cumulative newly-signed contract value and completed turnover, both USD 100M, each with YoY %.

  • mofcom_labor_cooperation({ start_period?, end_period?, limit? }) — overseas labour dispatch (对外劳务合作): cumulative workers dispatched (10,000-person units), split by contracted-engineering vs labour-cooperation route, plus the YoY change (an absolute figure, not a percent).

  • mofcom_fdi_utilised({ start_period?, end_period?, limit? }) — utilised inbound FDI (吸收外商直接投资): cumulative new FDI-enterprise count and, for periods before mid-2023, the cumulative dollar amount (USD 100M), each with YoY %.

  • mofcom_series_list() — the four series above with their Chinese/English names, units, and current earliest/latest period — a cheap discovery call.

start_period/end_period accept YYYYMM or YYYY-MM; omit both for full history. limit caps how many of the matched rows come back (newest first, default 24, max 500).

Every row is a year-to-date cumulative figure, not a standalone monthly flow — China's commerce ministry reports these as Jan-through-month totals that reset every January. Each tool's response restates this in its note field so a caller does not mistake e.g. September's cumulative total for September alone.

No per-country/region breakdown is available. The "count of countries/regions" field in mofcom_odi is exactly that — a count — not a split by destination. A separate MOFCOM "country statistics" section exists but covers unrelated macro indicators (GDP, CPI, trade balance) rather than ODI/contracting/labour by destination, and is out of scope for this pack.

Related MCP server: cnbs-mcp-server

Auth

Keyless. No cookie or session — just a same-site Referer header, which the pack sends on every call.

Data sources

  • Ministry of Commerce of the People's Republic of China (中华人民共和国商务部), 商务数据中心 (the commerce data centre) — 非金融类对外直接投资统计 (outward direct investment), 对外承包工程统计 (overseas contracted engineering), 对外劳务合作统计 (overseas labour dispatch), and 吸收外商直接投资月报 (monthly utilised inbound FDI) series.

Found via the data centre's own page-loader scripts, not curl-guessing — a direct API-path probe 404s, and the real calls only surface in each page's <slug>.js. All four are keyless POST endpoints with no cookie/session, just a Referer header, and all accept an optional start/end period filter.

The utilised-FDI series (mofcom_fdi_utilised) stopped carrying the monetary figure through this feed around mid-2023 — only the new-enterprise count has kept reporting since; the pack returns actual_fdi_usd_100m: null for those periods rather than inventing a number or dropping the row.

ODI history starts 2003, overseas contracting starts 1979, labour cooperation starts 2012, and utilised-FDI starts 1983 — ranges confirmed live via mofcom_series_list, not assumed.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/china-commerce/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 1861+ 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/mofcom_odi \
  -H 'Content-Type: application/json' \
  -d '{"start_period":"2026-01","end_period":"2026-09"}'

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

Run it from npm

@pipeworx/mcp-china-commerce is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/china-commerce/mcp endpoint shown above. It needs network access; there is no offline mode.

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

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

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 China Commerce data" })

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

More

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    Provides access to Chinese mainland financial data including A-stock quotes, financial statements, industry analysis, and macroeconomics through 42 MCP tools, with automatic data source fallback and no API key required.
    46
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides 46 no-authentication A-share (Chinese stock market) data tools covering quotes, financials, capital flows, sectors, announcements, macro data, and more, callable from any MCP client without API keys.
    127 npm
    2
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables querying China's official monthly merchandise trade statistics, including total exports/imports/balance, breakdowns by trading partner and HS commodity sections, and trade indices from the GACC English-language site.
    495 npm
    MIT