Skip to main content
Glama
Finland Law MCP Server

Finland Law MCP Server

by pipeworx-io

@pipeworx/

<One line: what this pack is and what data it returns. This line is the first thing a reader of docs/reference// sees.>

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

  • tool_name(...) — what it returns and which question it answers.

Related MCP server: se-eli-mcp

Auth

<One of: "Keyless." / "BYO only." / "Platform key (PLATFORM_<X>_KEY) with BYO override via ?_apiKey=." / "OAuth — provider in shared/src/providers.ts.">

<If the upstream gates access beyond registration — a manual approval step, a plan upgrade, an allowlist — say so HERE. Undocumented activation gates come back to us as bug reports, because a 403 looks identical to our outage.>

Data sources

  • , — what it serves (e.g. "INSEE, Sirene stock file"; "DILA, LEGI archive"; "Japan National Tax Agency, corporate number register"). Name the PUBLISHER and DATASET only — never a download path, directory, file name, endpoint, feed URL or query shape (Bruce, 2026-10-11: "let's not name the source file, just the source. I want to make it slightly harder to copy us."; CLAUDE.md step 9b). Routes live only in src/index.ts. A link to the publisher's human-facing page for ONE record (e.g. an opinion's own page) or its terms page is fine — that is the record, not a route.

<Anything the next person would otherwise rediscover the hard way: undocumented required headers, a host that moved, pagination that ignores its own sort parameter, fields that are lowercase-only. This section pays for itself.>

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/finland-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/fi_law_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"tietosuoja"}'

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

Run it from npm

@pipeworx/mcp-finland-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/finland-law/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "finland-law": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-finland-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 Finland 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
      A
      quality
      B
      maintenance
      Enables AI agents to search and retrieve consolidated Swedish statutes (SFS) from the Riksdagen open data API, with verifiable citations and persistent identifiers.
      4
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server providing direct, citable access to Finnish legislation by retrieving statute text from Finlex open data, enabling AI assistants to answer legal queries with accurate citations.
      MIT
    • A
      license
      A
      quality
      F
      maintenance
      Enables querying over 3,200 Dutch statutes (AVG, Wetboek van Strafrecht, Burgerlijk Wetboek, etc.) with verbatim, citation-grounded text from official sources, directly from MCP-compatible AI assistants.
      18
      49 npm
      15
      Apache 2.0