# Czso Cz [Health: Active]

**Category:** 🧮 Data Science Tools  
**Repository:** https://github.com/pipeworx-io/mcp-czso-cz  
**GitHub Stars:** 2  
**npm Downloads (last month):** 617  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/czso-cz

## Description
Czech Statistical Office (Český statistický úřad, ČSÚ) open-data MCP.

## Tools
Capabilities this server exposes over MCP:

- **list_datasets** — Browse the Czech Statistical Office (ČSÚ) open-data catalog of datasets ('datové sady'). Returns id (kod), version (verze), Czech title (nazev), status, and available time/territory levels. The full catalog is ~781 datasets; filter by a case-insensitive substring of the Czech title (the API has no server-side search) and page with limit/offset.
- **dataset_detail** — Full catalog metadata for one ČSÚ dataset by id (kod): description, keywords, indicators (ukazatele), dimension variants (variantyDimenze), selection rules, update periodicity and themes. Catalog layer only — use data_summary / get_data for the actual numbers.
- **data_summary** — Cheap content summary for a ČSÚ dataset from the data layer: number of data cells (pocetUdaju), covered time range (casovaDimenzeOd/Do), per-dimension value counts, and last-change/publish times. Use this before get_data to gauge size, since full datasets can be large. Version (verze) is auto-resolved from the catalog if omitted.
- **get_data** — Fetch the actual observations/values for a ČSÚ dataset as JSON-stat 2.0 (dimensions in `id`/`dimension`, cell counts in `size`, numbers in `value`). Verified live. NOTE: returns the complete dataset as a full cross-product, which is often large (hundreds of thousands of cells, 1MB+) — call data_summary first to check pocetUdaju. Version (verze) is auto-resolved from the catalog if omitted.

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

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

## Documentation

## What Czso Cz MCP server does

Czso Cz MCP server exposes the Czech Statistical Office (Český statistický úřad, ČSÚ) open-data catalog and its published datasets through MCP. It separates catalog exploration from data retrieval, which helps an agent identify the right dataset and understand its structure before requesting observations.

The catalog contains roughly 781 datasets. Dataset listings include the ČSÚ identifier (`kod`), version, Czech title, status, and available time and territory levels. Metadata for an individual dataset can include its description, keywords, indicators, dimension variants, selection rules, update frequency, and thematic classification.

The integration is an independent, unofficial connection and is not affiliated with, endorsed by, or published by ČSÚ.

## How it works

Connect through the hosted Pipeworx MCP endpoint or run the package locally over standard input and output. The hosted pack endpoint also exposes shared Pipeworx meta-tools, while the standalone package exposes only the ČSÚ-related tools. Both approaches use the same underlying source and tool set.

A practical query sequence is:

1. Search the catalog with `list_datasets`.
2. Inspect a candidate using `dataset_detail`.
3. Call `data_summary` to check the number of cells, time span, dimension sizes, and publication or modification timestamps.
4. Use `get_data` only when the complete observation set is appropriate.

When a version is omitted, the data tools resolve it from the catalog. Catalog filtering uses a case-insensitive substring of the Czech dataset title. Because the ČSÚ API does not provide server-side title search, filtering is performed by the service, with pagination through `limit` and `offset`.

## Setup and configuration

For a hosted connection, add the streamable HTTP endpoint to an MCP client:

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

The full Pipeworx gateway is also available at `https://gateway.pipeworx.io/mcp`. A pack endpoint lists the ČSÚ tools directly and includes shared gateway meta-tools; the full gateway lists tools from all available packs directly.

For local execution, use the npm package through a stdio configuration:

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

The local mode does not require a Pipeworx account or gateway round trip. No environment variables are required by the documented setup.

## Tools and capabilities

- `list_datasets` browses the ČSÚ catalog with title filtering and pagination.
- `dataset_detail` returns detailed catalog metadata for a dataset identifier.
- `data_summary` reports cell counts, time coverage, dimension value counts, and change or publication timestamps.
- `get_data` returns the complete dataset as JSON-stat 2.0, including dimension identifiers, dimension metadata, cell sizes, and values.
- The hosted gateway can also accept direct HTTP tool calls and natural-language requests through its shared routing tools.

## Limitations and notes

`get_data` returns the full cross-product of a dataset rather than a narrowly selected slice. Large datasets may contain hundreds of thousands of cells and produce responses of 1 MB or more, so `data_summary` should be used first to estimate the response size.

The catalog and data responses use Czech field names and dataset titles. The catalog's title filter is substring-based because the upstream API has no server-side search. The hosted endpoint's exact shared-tool inventory can change; its `initialize` response is authoritative for the tools exposed in a particular connection.

The direct HTTP interface can be used without an MCP client for initial calls, while local stdio execution provides only the ČSÚ pack tools and does not include Pipeworx-wide routing.

_Full upstream README: https://allmcps.com/mcp/czso-cz/readme_