Log inSubmit server
Statcan MCP logo

Statcan MCP

Queries Statistics Canada’s 8,200+ data tables for metadata and time-series data without an API key.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Statcan MCP

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-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "statcan-mcp"
      ]
    }
  }
}

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

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y statcan-mcp

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 3d ago.

Overview

  • statistics
  • canada
  • data
  • economic-indicators
  • mcp

The statcan-mcp MCP server gives MCP clients access to Statistics Canada’s Web Data Service and its 8,200+ data tables. It supports table discovery, metadata inspection, vector-based retrieval, coordinate-based retrieval, and vector ID lookup without requiring an API key. Use it for current or historical Canadian indicators such as CPI, GDP, labour force, housing, population, and trade. Its tools guide the workflow from finding a table to selecting dimensions and retrieving data.

Use cases

  • Search Statistics Canada tables by topic
  • Inspect dimensions before selecting data
  • Retrieve recent Canadian economic time series
  • Compare regional indicators by table coordinates
  • Decode an unknown Statistics Canada vector ID

Key features

  • Searches more than 8,200 Statistics Canada tables
  • Returns filterable table metadata
  • Retrieves data by vector ID or coordinate
  • Supports date ranges and latest-period queries
  • Decodes vector IDs and runtime code values
  • Requires no API key

Tools5

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

Self-reported~95 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 Today

Recent health check succeeded.

5/5 checks healthy over the last 40d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · statcan-mcp (npm)

Adoption & maintenance

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

npm downloads180Package downloads in the last 30 days.
Last commit4d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed5Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Statcan MCP works

What statcan-mcp MCP server does

The statcan-mcp MCP server translates Statistics Canada’s Web Data Service into tools that an MCP-compatible language model can call. The catalogue includes more than 8,200 tables covering indicators such as consumer prices, gross domestic product, labour force measures, housing starts, population, and trade.

The server is intended for data discovery and time-series retrieval. It can help an agent find a relevant table, understand its dimensions and available members, then request observations using either vector IDs or table coordinates. No Statistics Canada API key is required.

How it works

A typical request follows a discovery sequence:

  1. Search the table catalogue with keywords.
  2. Inspect a table’s dimensions and members.
  3. Choose either vector IDs or one member from each table dimension.
  4. Request a date range or the latest number of periods.

search_tables searches the full table catalogue. get_table_metadata returns the table structure and its members, with limits and keyword filters to keep responses manageable. This is useful for large dimensions, such as a CPI dimension with hundreds of members.

Vector IDs can be supplied with or without the v prefix. Coordinate inputs are padded automatically. Runtime decoding of Statistics Canada code sets turns numeric response fields into readable information, including scale and status notes.

Setup and configuration

The server runs through the package command and uses standard MCP client configuration. Claude Code can add it with:

Terminal
claude mcp add statcan -- npx -y statcan-mcp

For Claude Desktop, add a server entry that runs npx with -y statcan-mcp as its arguments. The same invocation is documented for Cursor, Windsurf, and other MCP clients. No environment variables or API credentials are specified as required.

Tools and capabilities

The statcan-mcp MCP server exposes five tools:

  • search_tables: Finds tables by keyword across the Statistics Canada catalogue.
  • get_table_metadata: Lists a table’s dimensions and members, with capping and filtering options.
  • get_data_by_vectors: Retrieves time-series observations for one or more vector IDs by date range or latest-period count.
  • get_data_by_coordinate: Retrieves a series by table and one selected member for each dimension.
  • get_series_info: Resolves a vector ID to its series title and source table.

These tools support questions such as comparing regional inflation, checking recent unemployment trends, finding housing-start figures, or identifying an unknown vector ID.

Limitations and notes

English output is supported currently; the underlying API also contains French fields, but French-language output is listed as future work. Full-table CSV downloads and streamable HTTP deployment are also roadmap items, so the documented server is focused on MCP tool access rather than bulk export or remote HTTP hosting.

The project is not affiliated with or endorsed by Statistics Canada. Its data is identified as Statistics Canada content used under the Statistics Canada Open Licence. API failures, including unknown vectors or invalid coordinates, are returned as MCP tool errors containing Statistics Canada’s message, allowing the calling model to correct its request. The server is released under the MIT license.

Read the full README View source on GitHub

Reviews

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

Frequently Asked Questions about Statcan MCP

statcan-mcp is an MCP server that connects language-model clients to Statistics Canada’s Web Data Service. Its main tools search more than 8,200 tables, inspect table metadata, retrieve time series by vector or coordinate, and identify vector IDs. It requires no API key and covers indicators including CPI, GDP, labour, housing, population, and trade.

Install it by running `npx -y statcan-mcp` through your MCP client. Claude Code uses `claude mcp add statcan -- npx -y statcan-mcp`; Claude Desktop requires a matching `mcpServers` configuration entry.

No, statcan-mcp does not require an API key. It accesses Statistics Canada’s Web Data Service through the configured MCP process.

Retrieve data by first searching for a table and inspecting its metadata, then calling either `get_data_by_vectors` or `get_data_by_coordinate`. Vector retrieval accepts date ranges or a latest-period count, while coordinate retrieval selects one member for each table dimension.

Not currently; English output is supported for now. French fields exist in the underlying API, and French-language output is listed on the project roadmap.

Related MCP servers

All in Data Science Tools All alternatives
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 MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/statcan-mcp?style=directory)](https://allmcps.com/mcp/statcan-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/statcan-mcp"><img src="https://allmcps.com/api/badge/statcan-mcp?style=directory" alt="Statcan MCP on AllMCPs" /></a>