# Cso Ie [Health: Active]

**Category:** 🧮 Data Science Tools  
**Repository:** https://github.com/pipeworx-io/mcp-cso-ie  
**GitHub Stars:** 0  
**npm Downloads (last month):** 463  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/cso-ie

## Description
Ireland Central Statistics Office (CSO) PxStat MCP.

## Tools
Capabilities this server exposes over MCP:

- **list_datasets** — Search the CSO catalog of ~12,600 Irish statistics tables. Returns matching tables with their matrix code (e.g. "CPM01"), label, dimensions, and last-updated date. The full catalog is large, so always pass a keyword query to narrow it.
- **dataset_metadata** — Get the structure of one CSO table by matrix code: its dimensions, the category codes + human labels for each dimension, size, and last-updated date. Use this to discover valid dimension codes before calling get_dataset with filters.
- **get_dataset** — Read a full CSO table as JSON-stat 2.0 (dimensions + flat value array). Some tables are large (the CPI table is ~60k values); use dataset_metadata first to gauge size, or use query_dataset to fetch a filtered slice instead.
- **query_dataset** — Read a FILTERED slice of a CSO table via JSON-RPC. Pass a map of dimension code -> array of category index values to keep (get the dimension codes and category index values from dataset_metadata). Returns JSON-stat 2.0 covering only the selected cells — far smaller than get_dataset.

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

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

## Documentation

## What Cso Ie does

Cso Ie exposes Ireland’s Central Statistics Office (CSO) PxStat data through MCP. It helps an agent find relevant tables in the CSO catalog, understand their structure, and retrieve statistical values in JSON-stat 2.0 format.

The catalog contains approximately 12,600 Irish statistics tables. Search results include each matching table’s matrix code, label, dimensions, and last-updated date. Matrix codes, such as `CPM01`, identify individual tables for subsequent requests.

## How it works

A typical workflow starts with `list_datasets`, using a keyword query to narrow the catalog. After selecting a matrix code, call `dataset_metadata` to inspect the table’s dimensions, category codes, human-readable labels, size, and update date.

Use `get_dataset` when the complete table is appropriate. It returns JSON-stat 2.0 with dimension information and a flat value array. For larger tables, `query_dataset` returns only selected cells. Its filters map each dimension code to an array of category index values, which should be obtained from `dataset_metadata` first.

The hosted version is available at `https://gateway.pipeworx.io/cso-ie/mcp`. It can also be accessed through the full Pipeworx gateway at `https://gateway.pipeworx.io/mcp`; the scoped endpoint lists this pack’s tools directly while the gateway can route across its broader catalog through shared tools such as `ask_pipeworx`.

## Setup and configuration

For a hosted MCP connection, add the following server URL to an MCP client:

```json
{
  "mcpServers": {
    "cso-ie": {
      "url": "https://gateway.pipeworx.io/cso-ie/mcp"
    }
  }
}
```

The package can instead run locally over stdio, without a Pipeworx account or gateway round trip:

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

Run `npx -y @pipeworx/mcp-cso-ie` directly to verify that the local process starts. The local process handles MCP `initialize`, `tools/list`, and `tools/call` requests for the Cso Ie tools.

Without an MCP client, hosted tools can be called over HTTP. For example, send a JSON POST request to `https://gateway.pipeworx.io/v1/tools/cso_ie_list_datasets` with a `query` field. The first calls do not require an account.

## Tools and capabilities

- `list_datasets`: Searches the CSO catalog using a keyword query and returns matching table details.
- `dataset_metadata`: Describes a table’s dimensions, category codes, labels, size, and update date.
- `get_dataset`: Retrieves a complete table as JSON-stat 2.0.
- `query_dataset`: Retrieves a filtered JSON-stat 2.0 slice using dimension category indexes.

## Limitations and notes

Complete table responses can be large; the CPI table is cited as containing approximately 60,000 values. Inspect metadata before downloading a full table and use `query_dataset` when only selected dimensions or categories are needed.

The hosted scoped endpoint includes shared Pipeworx gateway meta-tools in addition to the four Cso Ie tools. The local stdio package exposes only the pack’s tools. Cso Ie is an independent, unofficial CSO integration and is not affiliated with, endorsed by, or published by the Central Statistics Office.

_Full upstream README: https://allmcps.com/mcp/cso-ie/readme_