
Connects Claude to the Netherlands' national open data portal (data.overheid.nl) via its CKAN API. You get two main tools: list_organizations to browse ministries, agencies, and provinces, and list_groups for thematic categories (though the portal currently returns no groups). The server is part of Pipeworx's gateway ecosystem, so you can either connect directly or use the broader Pipeworx gateway for 708+ data sources. Includes an ask_pipeworx tool that lets you query in plain English instead of calling CKAN endpoints directly. Reach for this when you need Dutch government datasets, budget data, or public sector information without manually working through CKAN's API documentation.
data.overheid.nl MCP — the Netherlands national open-data portal (CKAN API).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_datasets | Search the data.overheid.nl catalogue of Dutch government open data (CKAN package_search). Returns matching datasets with titles/descriptions (mostly Dutch). Query may be Dutch or English; Dutch matches more. |
dataset_details | Full dataset record by id or slug (CKAN package_show), including its resources. Each resource has a download "url" and "format" (CSV/JSON/etc.) — the portal is metadata-only, so fetch those URLs to get the actual data. |
list_organizations | List publishing organizations (ministries/agencies/provinces) on data.overheid.nl (CKAN organization_list). Use an org "name" in search_datasets fq, e.g. "organization:". |
list_groups | List thematic groups/categories on data.overheid.nl (CKAN group_list). Note: this portal currently exposes no groups (returns an empty list) — prefer fq facets on search_datasets to narrow by theme. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"overheid-nl": {
"url": "https://gateway.pipeworx.io/overheid-nl/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/overheid-nl/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Overheid Nl data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/overheid_nl_search_datasets \
-H 'Content-Type: application/json' \
-d '{"query":"onderwijs"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/overheid_nl_search_datasets. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.