pipeworx-io/mcp-avoindata-fi

Finland Open Data (www.avoindata.fi/data/en) CKAN MCP.
Part of Pipeworx — an MCP gateway connecting AI agents to 1863+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
## Tools
| Tool | Description |
| searchdatasets | Search Finland Open Data (Finland) for datasets by keyword. Returns each dataset's id/name, title, organization, and its resources (each with a resourceid for queryresource). |
| dataset | Show full metadata for one Finland Open Data dataset by id or name (from searchdatasets), including all resources and their resourceids. |
| queryresource | Pull rows from a tabular Finland Open Data resource (CKAN DataStore) by resourceid (from a dataset's resources). Optional full-text q, limit, offset. Note: only resources with the DataStore enabled are queryable. |
## Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
json
"mcpServers": {
"avoindata-fi": {
"url": "https://gateway.pipeworx.io/avoindata-fi/mcp"
### What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/avoindata-fi/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — askpipeworx,
discovertools, searchwithin, 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
askpipeworx, 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:
json
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
Both URLs reach the same gateway and the same 1863+ data sources. The
only difference is which pack's tools are listed directly; askpipeworx
reaches all of them from either one.
## No MCP client? Call it over HTTP
bash
curl -X POST https://gateway.pipeworx.io/v1/tools/avoindatafisearchdatasets \
-H 'Content-Type: application/json' \
-d '{"query":"population statistics"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/avoindatafisearchdatasets. Find one: POST https://gateway.pipeworx.io/v1/tools/searchpacks with {"query":"..."}.
## Run it from npm
@pipeworx/mcp-avoindata-fi is a local stdio bridge to the Pipeworx gateway: your MCP client