# Ine Es [Health: Active]

**Category:** 🧮 Data Science Tools  
**Repository:** https://github.com/pipeworx-io/mcp-ine-es  
**GitHub Stars:** 0  
**npm Downloads (last month):** 474  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/ine-es

## Description
INE Spain (Instituto Nacional de Estadística) Tempus3 JSON API MCP.

## Tools
Capabilities this server exposes over MCP:

- **list_operations** — List all available INE statistical operations (Spain). Each has a numeric Id, a Codigo (e.g. "IPC"=CPI, "EPA"=labor force survey), and a Nombre. Use the Codigo or Id with tables_for_operation.
- **tables_for_operation** — List the statistical tables belonging to one INE operation. operationId may be the numeric Id (e.g. 25) or the operation code (e.g. "IPC", "EPA"). Each table has an Id used by series_in_table / table_data.
- **series_in_table** — List the data series contained in an INE table. Each series has a COD (series code, e.g. "IPC251852") and a Nombre describing the breakdown. Pass a COD to series_data.
- **table_data** — Fetch data points for ALL series in an INE table at once. Use nult=N for the last N periods, or date="YYYYMMDD:" for everything from that date on (trailing colon = open-ended range). Each series object carries a Data[] array of {Fecha (epoch ms), Anyo, Valor}.
- **series_data** — Fetch data for ONE INE series by its code. Use nult=N for the last N periods, or date="YYYYMMDD:" for from that date on. Returns the series with its Data[] array of {Fecha (epoch ms), Anyo, Valor} points.
- **variable_values** — List the values of an INE classification variable (e.g. provinces, age groups, ECOICOP groups). With no variableId, lists all variables; with a variableId, lists that variable's allowed values (each has an Id, Codigo, Nombre). Useful for understanding the breakdowns inside tables.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "ine-es": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-ine-es"]
  }
}
```

## Documentation

## What Ine Es MCP server does

The Ine Es MCP server exposes Spain’s Instituto Nacional de Estadística (INE) Tempus3 JSON API through MCP. It gives an agent a structured path from broad statistical catalog discovery to specific observations. An agent can first identify an operation, find its tables, inspect the series inside a table, and then request data for the selected series.

The server covers statistical metadata as well as observations. Operations include identifiers, codes, and names; tables have identifiers; series have codes and descriptive names; and classification variables provide allowed values such as provinces, age groups, or ECOICOP groups.

## How it works

The discovery sequence is operation, table, series, and data. `list_operations` returns INE operations and their numeric IDs and codes. `tables_for_operation` accepts either form of operation identifier. `series_in_table` then exposes the series codes needed by `series_data`.

Use `series_data` when one series is required. Use `table_data` when all series in a table should be returned together. Both data tools support a count of recent periods through `nult=N`, or an open-ended date filter such as `YYYYMMDD:`. Returned observations contain `Fecha` as epoch milliseconds, along with `Anyo` and `Valor` fields.

`variable_values` helps interpret table breakdowns. With no variable identifier, it lists available variables; with one, it returns the permitted IDs, codes, and names for that classification.

## Setup and configuration

The Ine Es MCP server can run as a local stdio process with the `@pipeworx/mcp-ine-es` package. An MCP client starts it with `npx -y @pipeworx/mcp-ine-es`; the process communicates through standard input and output and exposes only this pack’s six tools.

It can also be connected through the Pipeworx gateway at `https://gateway.pipeworx.io/ine-es/mcp`. The gateway endpoint includes the Ine Es tools plus shared Pipeworx meta-tools. The full gateway endpoint at `https://gateway.pipeworx.io/mcp` exposes the wider catalog directly.

The tools can also be called over HTTP. For example, the gateway provides `/v1/tools/list_operations`, which accepts a JSON request and a language field in the documented example.

## Tools and capabilities

- `list_operations`: discover INE statistical operations.
- `tables_for_operation`: list tables for an operation ID or code.
- `series_in_table`: inspect the series contained in a table.
- `series_data`: retrieve observations for one series.
- `table_data`: retrieve observations for every series in a table.
- `variable_values`: inspect classification variables and their values.

## Limitations and notes

The Ine Es MCP server is focused on INE Spain data exposed through the Tempus3 JSON API. It does not provide a separate tool for arbitrary external datasets. Gateway connections list additional shared tools, so the number of tools shown by an MCP client may exceed the six pack-specific tools. A local stdio connection avoids those gateway meta-tools but does not provide Pipeworx-wide routing through `ask_pipeworx`.

_Full upstream README: https://allmcps.com/mcp/ine-es/readme_