
Connects Claude to New Zealand's open data catalog via the CKAN API. You get five tools: package_search for full-text queries across datasets, organization_list and group_list for browsing publishers and categories, tag_list for taxonomy exploration, and recently_changed_packages for tracking updates. Runs through Pipeworx's gateway, which means you can either point directly at data.govt.nz or connect to their full network of 673+ sources. Useful when you're analyzing NZ public sector data, comparing datasets across government agencies, or need to programmatically discover what's available without clicking through a web portal. Includes an ask_pipeworx wrapper that takes natural language questions instead of manual tool calls.
data.govt.nz MCP — NZ government CKAN open-data catalogue, keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
package_list(limit?, offset?) — list dataset names (paged)package_search(q?, fq?, sort?, rows?, start?, facet_field?) — full-text + faceted searchpackage_show(id) — single dataset (id or name)organization_list(all_fields?, limit?, offset?) — publishing orgsorganization_show(id, include_datasets?) — single orggroup_list(all_fields?, limit?, offset?) — groups/categoriesgroup_show(id, include_datasets?) — single grouptag_list(query?, all_fields?, vocabulary_id?) — tag listtag_show(id, include_datasets?) — single tagrecently_changed_packages(limit?, offset?) — recent updatesresource_show(id) — single resourcehttps://catalogue.data.govt.nz/api/3/action
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"data-govt-nz": {
"url": "https://gateway.pipeworx.io/data-govt-nz/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/data-govt-nz/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 Data Govt Nz data" })
The gateway picks the right tool and fills the arguments automatically.
MIT