Skip to main content
Glama
@pipeworx/bis

@pipeworx/bis

Official
by pipeworx-io

@pipeworx/bis

BIS (Bank for International Settlements) MCP — central-bank and global-financial statistics over the BIS SDMX v2 API. No auth.

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

  • bis_credit_gap(country, start_period?, end_period?, limit?) — credit-to-GDP ratio, its long-run HP-filter trend, and the gap between them, per quarter, for one country. The gap is the Basel III reference indicator for the countercyclical capital buffer. Accepts a country name or ISO alpha-2 code; 44 economies plus the euro area aggregate (XM).

  • list_curated_flows(topic?) — pre-vetted dataflow refs by topic (rates, fx, banking, debt, credit, property, derivatives, prices).

  • search_dataflows(query, limit?) — keyword search over the full BIS dataflow registry; returns flow_refs ready for fetch_dataset.

  • fetch_dataset(flow_ref, key?, start_period?, end_period?, limit?) — tidy rows from any BIS dataflow.

Related MCP server: mcp-ecb

Auth

None. BIS publishes these statistics openly and applies no key or quota.

Notes on the upstream API

  • flow_ref carries a version and the version is not always 1.0. BIS re-versions dataflows in place (WS_TC is 2.0), and a stale version returns an empty result rather than an error. Take refs from list_curated_flows or search_dataflows instead of assuming one.

  • Keys are positional over the flow's own dimensions, dot-separated — e.g. Q.US... on WS_CREDIT_GAP, whose key is FREQ.BORROWERS_CTY.TC_BORROWERS.TC_LENDERS.CG_DTYPE. Leave a position empty to not filter on it. When a key matches nothing, fetch_dataset names the flow's actual dimensions back to you.

  • Rows carry both the code and its meaning. Every coded column arrives with a <COLUMN>_label companion (CG_DTYPE: "C" / CG_DTYPE_label: "Credit-to-GDP gaps (actual-trend)"), because BIS's coded values are opaque on their own.

  • The banking and debt-securities flows are multi-megabyte unbounded — pass start_period / end_period.

Data sources

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/bis/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/bis_list_curated_flows \
  -H 'Content-Type: application/json' \
  -d '{"topic":"rates"}'

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

Run it from npm

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

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

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 Bis data" })

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

More

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Provides access to World Bank economic and country data without an API key, allowing users to search countries, fetch indicator time series, and compare latest values.
    5
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides access to European Central Bank statistical data through SDMX data flows, enabling querying and listing of data flows via natural language or direct tool calls.
    526 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables searching, exploring, and querying over 1,500 OECD statistical datasets via SDMX, covering national accounts, employment, trade, PISA, health, and more.
    519 npm
    4
    Apache 2.0