Skip to main content
Glama

mcp-ecos-kr

ECOS — Bank of Korea Economic Statistics System.

Part of Pipeworx — an MCP gateway connecting AI agents to 1863+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

Tool

Description

ecos_key_indicators

Bank of Korea headline economic indicators: M1/M2 money supply, KRW/USD + KRW/JPY exchange rates, base interest rate, CPI, PPI, GDP growth, current account balance, household debt, unemployment, housing index — 101 series total in one call. Each row: indicator name, current value, cycle date, unit. Use for "what is Korea's [exchange rate / interest rate / CPI / GDP] right now". Updates daily.

ecos_search_tables

Search Bank of Korea ECOS statistic tables — 800+ official Korean economic series across monetary policy, exchange rates, prices, balance of payments, GDP, real estate, household credit, etc. Returns stat_code + Korean name + cycle (A annual / Q quarterly / M monthly / D daily). Use as a directory before ecos_get_series. q is matched substring-wise against the Korean name; pass blank to browse top-N.

ecos_series_items

List the items (sub-series) within a Bank of Korea ECOS statistic table. Most stat_codes have multiple sub-items (e.g., the exchange-rate table has rows per currency: USD, JPY, EUR, ...). Pass the stat_code from ecos_search_tables; returns item_code, item_name, cycle, data_count, start/end period. Use to discover the exact item codes needed by ecos_get_series.

ecos_get_series

Fetch a time series from Bank of Korea ECOS. Pass stat_code + cycle (A/Q/M/D) + start/end period. Date format matches the cycle: yearly = "2024", quarterly = "2024Q3", monthly = "202403", daily = "20240315". Optionally narrow to specific item_code(s) via item1/item2/item3/item4. Returns rows with stat_name, item_name, unit, time, data_value. Use after ecos_search_tables + ecos_series_items to discover codes.

Related MCP server: kosis-mcp

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/ecos-kr/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 1863+ 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/ecos_key_indicators \
  -H 'Content-Type: application/json' \
  -d '{"limit":50}'

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

Run it from npm

@pipeworx/mcp-ecos-kr 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/ecos-kr/mcp endpoint shown above. It needs network access; there is no offline mode.

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

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 Ecos Kr 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
    D
    maintenance
    Enables querying Korean official statistics from KOSIS via natural language in MCP clients like Claude Desktop, wrapping the KOSIS OpenAPI for search, data retrieval, and metadata exploration.
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Korean public-data MCP servers for AI agents, enabling natural language queries to KOSIS statistics and other Korean official data sources without requiring local accounts or API keys.
    -
  • A
    license
    A
    quality
    D
    maintenance
    MCP server serving official statistics from major data agencies (Statistics Canada, FRED, BLS, World Bank, etc.) as tools with provenance and verification, enabling search, retrieval, analysis, and monitoring via natural language.
    11
    63 npm
    MIT