@pipeworx/datos-co

Colombia national open data: generic dataset search/query tools, plus a lookup for Colombian collective investment funds (fondos de inversión colectiva, FIC).

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

• search_datasets(q), dataset_columns(datasetId), query_dataset(datasetId, $where, ...) — generic access to any dataset on the national open-data portal.

• co_fic_search(name) — find a fund by name or by its management company. Case, accents and word order do not matter; one typo per word is tolerated. Returns fund_code, entity and fund name, or found:false with the closest names.

• co_fic_unit_value(fund | fund_code, date?, from?, to?, participation_class?) — unit value (valor de la unidad), fund size, investors and daily/monthly/semester/annual returns per participation class. Default is the latest published day.

Related MCP server: secop-mcp-server

Behaviour worth knowing

• A name that matches nothing returns found:false with reason: "no_fund_matches_all_words" and the closest funds. A name that matches several returns reason: "ambiguous_fund_name" with candidates; pass fund_code to choose. A malformed date or missing fund is an error, not a miss.

• Publication lags a few days; data_as_of is the latest published day and fund_last_reported the fund's own last row. A requested date past that returns fund_matched_but_no_rows_for_request.

• Duplicate upstream rows are collapsed to one per day and participation class.

• Return fields: the regulator publishes percentages but does not document their basis. Our reading, verified against the same unit-value series: each is an effective annual rate (compounded to 365 days) over a trailing 1 / 30 / 183 / 365-day window, so the daily figure is annualised, not the day's price change.

• Only funds that reported in the last 30 days are searchable.

Auth

Keyless. No platform key.

Data source

Superintendencia Financiera de Colombia, daily collective investment fund (FIC) series, published on the national open-data portal. Proxied per request; nothing is mirrored.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/datos-co/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/datos_co_search_datasets \
  -H 'Content-Type: application/json' \
  -d '{"q":"covid"}'

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

Run it from npm

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

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

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 Datos Co data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT