
Connects Claude to Argentina's official time series API at apis.datos.gob.ar, giving you access to national economic and statistical data published by the Argentine government. Part of the Pipeworx gateway ecosystem, which routes requests through a unified endpoint and includes an ask_pipeworx tool that translates natural language questions into proper API calls. You can use it standalone or as part of the full Pipeworx gateway that bundles 673+ data sources. Useful when you need Argentine inflation rates, GDP figures, employment stats, or other official time series data without writing custom API integration code. Runs over streamable HTTP transport.
Argentina "Series de Tiempo" MCP — national time-series API (apis.datos.gob.ar).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_series | Search Argentina's national time-series catalog (apis.datos.gob.ar) for series matching a keyword. Titles/descriptions are in Spanish (e.g. q="inflacion", "pbi", "emae", "tipo de cambio", "desempleo"). Returns matching series with their ids (use these with get_series), titles, units, frequency, date coverage, dataset and source. |
get_series | Fetch observations for one or more Argentine time series by id (ids come from search_series). Data is official Argentine statistics; titles are in Spanish. Pass multiple comma-separated ids to align several series on the same dates. Use collapse to resample (e.g. monthly→yearly avg) and representation_mode to transform values (e.g. percent change vs a year ago). Returns rows of [date, value, ...] plus metadata. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"datos-ar": {
"url": "https://gateway.pipeworx.io/datos-ar/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/datos-ar/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Ar data" })
The gateway picks the right tool and fills the arguments automatically.
MIT