{
  "markdown": "# mcp-czso-cz\n\nCzech Statistical Office (Český statistický úřad, ČSÚ) open-data MCP.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `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. |\n| `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. |\n| `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. |\n| `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. |\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"czso-cz\": {\n      \"url\": \"https://gateway.pipeworx.io/czso-cz/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/czso-cz/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Czso Cz data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 3694,
  "sha": "cfe06a86c96b5556aa876d99800e8db5308c190ca08e5b49a2d0e6bb53e15032",
  "repo_slug": "pipeworx-io/mcp-czso-cz",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_czso_cz_87448c99/readme"
}