Statcan logo

Statcan

Accesses Statistics Canada indicators, series, cube metadata, observations, change feeds, and CSV download URLs through MCP.

Install Statcan

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "statcan": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-statcan"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

Statcan MCP server connects AI agents to Statistics Canada's keyless Web Data Service for Canadian indicators, time series, and statistical cubes. It offers shortcuts for CPI, unemployment, GDP, and population, alongside catalogue and cube tools for broader datasets. Use it when an agent needs official Canadian statistics, filtered cube observations, update detection, or a direct full-table CSV URL. The hosted endpoint requires no account, while the npm bridge can use an optional Pipeworx API key for a higher daily call allowance.

Use cases

  • Retrieve Canadian CPI, unemployment, GDP, or population indicators
  • Find vector IDs and fetch observations from a StatCan cube
  • Inspect cube dimensions before constructing a coordinate query
  • Detect series updated on a release date
  • Generate a direct CSV download URL for a full cube

Key features

  • Keyless access to Statistics Canada Web Data Service
  • Headline indicators for Canada and its provinces or territories
  • Vector- and cube-based data retrieval
  • Filtered vector enumeration with coordinates and member labels
  • Change-date detection for updated series
  • Curated whole-table responses and live CSV URLs

Tools7

What Statcan lets your agent do. Expand a tool for its parameters.

Self-reported~391 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

13/13 checks healthy over the last 68d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 3d ago via OSV.dev · @pipeworx/mcp-statcan (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads1.1kPackage downloads in the last 30 days.
Last commit5d agoMost recent push to the default branch.
Tools exposed7Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Statcan works

What Statcan MCP server does

Statcan MCP server exposes Statistics Canada data through MCP, covering headline indicators and the broader table catalogue. Its indicator tool resolves common requests such as Canadian CPI, unemployment, GDP, and population by province or territory. The series tool accepts a numeric StatCan vector ID and returns recent observations with the series title.

For less common datasets, the cube workflow provides catalogue discovery, metadata, vector enumeration, coordinate-based observations, and CSV download links. The service also includes a curated whole-table lookup for selected high-demand tables. That lookup can return many coordinates and reference dates in one paged response, with dimension labels stored in a generic members object.

How it works

The hosted MCP endpoint is available at https://gateway.pipeworx.io/statcan/mcp. A full Pipeworx gateway endpoint is also available at https://gateway.pipeworx.io/mcp; both reach the same gateway, while the scoped endpoint lists StatCan tools directly and also exposes shared Pipeworx meta-tools.

A typical cube query starts with statcan_list_cubes, followed by statcan_cube_metadata to inspect dimensions and members. Use statcan_cube_vectors to map filtered dimension members to vector IDs and coordinates, then call statcan_series or statcan_cube_data for observations. Product IDs may use either the eight-digit WDS form or StatCan's public table-number format.

statcan_cube_data handles one coordinate per request. Coordinates contain ten dot-separated positions, with unused dimensions represented by trailing zeros. Filter wide cubes before enumerating them, because unfiltered dimensions can produce a large cross-product. statcan_changed_series supports release-date checks, and statcan_csv_url returns a live StatCan download URL without downloading the file itself.

Setup and configuration

Add the hosted endpoint to an MCP client with a server entry such as:

config.json
{
  "mcpServers": {
    "statcan": {
      "url": "https://gateway.pipeworx.io/statcan/mcp"
    }
  }
}

A local stdio bridge is available through npm:

config.json
{
  "mcpServers": {
    "statcan": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-statcan"]
    }
  }
}

The bridge forwards requests to the hosted gateway and needs network access. It works anonymously with a daily limit of 50 calls. Setting PIPEWORX_API_KEY with a free Pipeworx account raises the limit to 200 calls per day. The hosted StatCan connection itself is keyless and does not require an authentication header.

The tools can also be called over HTTP, for example by posting JSON to https://gateway.pipeworx.io/v1/tools/statcan_indicator.

Tools and capabilities

  • statcan_indicator: Retrieves common Canadian indicators by name and geography.
  • statcan_series: Fetches observations for a numeric StatCan vector ID.
  • statcan_list_cubes: Lists available cubes with product IDs, titles, CANSIM IDs, dimension counts, and release dates.
  • statcan_cube_metadata: Returns cube dimensions, members, frequency, geography, and release details.
  • statcan_cube_vectors: Enumerates vector IDs and coordinates, with optional dimension filters.
  • statcan_cube_data: Returns the latest requested observations for one cube coordinate.
  • statcan_table: Reads paged data from a curated set of cached tables, including member labels and data timestamps.
  • statcan_changed_series: Finds series updated on a specified date.
  • statcan_csv_url: Produces a direct URL for a complete cube CSV export.

Limitations and notes

The statcan_table dataset is curated rather than universal. Unsupported product IDs return an error listing the cached IDs; use live coordinate queries or a CSV URL for other tables. Cube metadata describes dimensions and members but does not itself provide vector IDs, so vector enumeration is the bridge to a usable series.

A terminated series has stopped publishing, and a cube's overall end date should not be treated as that series' last observation. Responses from curated tables include a pipeline timestamp and identify the Statistics Canada Open Licence. Reuse of that data requires source acknowledgment and must not imply endorsement by Statistics Canada. The integration is independent and unofficial.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Statcan

Statcan is an MCP server that connects AI agents to Statistics Canada’s Web Data Service. Its main tools retrieve headline indicators, fetch vector-based time series, list cubes, inspect cube metadata, enumerate vectors, query cube coordinates, detect changed series, and return CSV download URLs for official Canadian statistics.

Add the hosted URL `https://gateway.pipeworx.io/statcan/mcp` to your MCP client, or run the local bridge with `npx -y @pipeworx/mcp-statcan`. The npm bridge forwards calls to the hosted gateway, needs network access, and can run without an API key.

Yes, Statcan works with Cursor through its standard hosted MCP endpoint or the npm stdio bridge. Add `https://gateway.pipeworx.io/statcan/mcp` as the server URL, or configure the command `npx` with `-y @pipeworx/mcp-statcan`.

No, an API key is not required for the hosted connection or anonymous npm-bridge calls. Anonymous bridge usage is capped at 50 calls per day; setting `PIPEWORX_API_KEY` raises the limit to 200 calls per day with a free Pipeworx account.

Start with `statcan_list_cubes` and `statcan_cube_metadata`, then use `statcan_cube_vectors` to obtain a vector ID or coordinate. Call `statcan_cube_data` with a known ten-position coordinate, or use `statcan_series` with the resulting vector ID.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewStatcan AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/statcan?style=directory)](https://allmcps.com/mcp/statcan)
HTML Embed
<a href="https://allmcps.com/mcp/statcan"><img src="https://allmcps.com/api/badge/statcan?style=directory" alt="Statcan on AllMCPs" /></a>