
Connects Claude to Canada's national open data catalogue via the CKAN API at open.canada.ca. Part of the Pipeworx gateway system, which routes requests to 673+ data sources through a unified interface. The setup is straightforward: point your MCP client at the Pipeworx gateway URL and you can query Canadian government datasets using either specific CKAN tools or the ask_pipeworx helper that interprets plain English questions. You'd reach for this when building applications that need programmatic access to federal datasets like census data, geospatial information, or public records without manually wrangling CKAN's API endpoints.
open.canada.ca MCP — Canada's national open-data catalogue (CKAN). Keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
search(query, fq?, rows?, start?) — CKAN package_searchpackage(id) — single dataset by id or slugorganizations(limit?) — publishersgroups(limit?) — themes/groupshttps://open.canada.ca/data/api/3/
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"opendata-canada": {
"url": "https://gateway.pipeworx.io/opendata-canada/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/opendata-canada/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 Opendata Canada data" })
The gateway picks the right tool and fills the arguments automatically.
MIT