Skip to main content
Glama

@pipeworx/czech-law

Czech national legislation from e-Sbírka, the Collection of Laws published by the Ministry of the Interior: search laws, decrees, regulations and constitutional acts (and treaties and Constitutional Court rulings) by title or words in the text, then read a regulation's record and its text, whole or one paragraph (§) at a time, in its current wording or as it stood on a past date. Original Czech text, with the collection citation, effective dates and amending acts.

Part of Pipeworx — an MCP gateway connecting AI agents to 1905+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

  • cz_law_search(query, in_force_only?, start?) — find regulations by Czech title words, words from the text, or a number such as 262/2006. Returns id (262/2006 Sb.), title, status (in force, repealed, promulgated without effect), promulgation date and a link. 50 per page; next_start continues. Relevance-ranked: amending acts and court rulings that cite a law also match, so in_force_only helps.

  • cz_law_get(id, section?, date?, max_chars?, offset?) — one regulation by collection number: title, citation, whether the wording returned is current, past or future, its effective window, when the law first took effect, repeal date and repealing act, amending acts, and the text. section returns one § (52, 73a) or, for constitutional acts, an article (čl. 5); date returns the wording in force on that day. Without section the text is capped at max_chars and offset reads on.

Related MCP server: Slov-Lex MCP Server

Auth

Keyless. The Ministry also runs a registered programming interface that needs an access key; this pack does not use it.

Data sources

  • Czech Republic, Ministry of the Interior, e-Sbírka (Collection of Laws) — laws and other legal acts as promulgated and as consolidated for each period in force, with amendment and repeal data.

wording says whether the text returned is the current wording, a past or a future one; in_force is true only for the current wording. The consolidated wording is the collection's own text for that period. Superscript numbers in the text appear as ^n. Very long laws are read in pages: a section search covers the first eight thousand fragments. data_as_of is the date of the live read. Read live on each call; nothing is copied. A search or lookup that finds nothing returns empty_reason, not an empty success. EU law is not in this pack (see the EUR-Lex pack); company data is in the Czech company-register pack.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "czech-law": {
      "url": "https://gateway.pipeworx.io/czech-law/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/czech-law/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 1905+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/cz_law_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"zákoník práce","in_force_only":true}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/cz_law_search. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-czech-law is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/czech-law/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "czech-law": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-czech-law"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

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 Czech Law data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      Enables querying and analyzing Slovak legislation via natural language, including full-text search, provision retrieval, and EU law integration.
      63 npm
      2
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables searching and reading Slovenian national regulations from the official PISRS register by title, abbreviation, or words in the text, returning full texts or single articles with Official Gazette citations, amendment history, and status. Original Slovenian text is read live, with consolidated or originally published versions selectable per request.
      MIT