<a href="https://www.statcan.gc.ca/en/start" target="_blank"><img src="assets/StatCan-Header.png" alt="Statistics Canada MCP Server"></a>

Statistics Canada MCP Server

<a href="https://www.python.org/downloads/" target="_blank"><img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="Python 3.10+"></a> <a href="https://opensource.org/licenses/MIT" target="_blank"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a> <a href="https://modelcontextprotocol.io/" target="_blank"><img src="https://img.shields.io/badge/MCP-ModelContextProtocol-green.svg" alt="MCP"></a> <a href="https://github.com/Aryan-Jhaveri" target="_blank"><img src="https://img.shields.io/badge/GitHub-Aryan--Jhaveri-lightgrey?logo=github" alt="GitHub"></a>

MCP server for Statistics Canada's Web Data Service (WDS) and SDMX REST API. Gives any MCP client — Claude, Cursor, VS Code Copilot, Gemini, and more — structured access to Canadian statistical data.

Hosted on Render — no install required for most users. See Quick Start.

⚠️ LLMs may fabricate data. Always verify important figures against official Statistics Canada sources.

Table of Contents

• Quick Start
• Setup by Client
• Examples
• Features & Tools
• Project Structure
• Known Issues

Quick Start

Pick the option that fits you. You don't need to install anything for Option 1.

Option 1 — Use the hosted server (recommended)

Connect directly to the public server on Render. No uv, no terminal, no local setup.

Claude Desktop

1. Open Settings (⌘,) → Connectors → Add Custom Connector
2. Name: mcp-statcan
3. URL: https://mcp-statcan.onrender.com/mcp
4. Save and restart Claude Desktop

Claude Code

claude mcp add statcan --transport http https://mcp-statcan.onrender.com/mcp --scope global

The hosted server provides all WDS + SDMX tools (~15 tools). No SQLite/DB tools — those require local setup (Option 3).

Option 2 — Self-host HTTP (WDS + SDMX, no DB)

Run a local server with the same tools as the hosted version. Useful if the hosted server is down or you need a private setup.

Step 1 — Install uv if you don't have it:

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Step 2 — Start the server in a terminal and leave it running:

uvx statcan-mcp-server --transport http
# Listening at http://localhost:8000

Step 3 — Connect your client to http://localhost:8000/mcp — see Setup by Client below.

Option 3 — Full local setup (WDS + SDMX + SQLite)

Everything from Option 2, plus database tools for storing and querying data with SQL. Runs via stdio — no separate server process.

Step 1 — Install uv (same as above).

Step 2 — Configure your client with the stdio snippets in Setup by Client below.

That's it. uvx downloads and runs the server automatically on first use.

Setup by Client

Hosted server (Option 1)

Claude Desktop — Settings → Connectors → Add Custom Connector

• Name: mcp-statcan
• URL: https://mcp-statcan.onrender.com/mcp

Claude Code

claude mcp add statcan --transport http https://mcp-statcan.onrender.com/mcp --scope global

Cursor — .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "statcan": {
      "url": "https://mcp-statcan.onrender.com/mcp"
    }
  }
}

VS Code (GitHub Copilot) — .vscode/mcp.json:

{
  "servers": {
    "statcan": {
      "type": "http",
      "url": "https://mcp-statcan.onrender.com/mcp"
    }
  }
}

Self-hosted HTTP (Option 2)

Start uvx statcan-mcp-server --transport http first, then configure your client.

Most clients need mcp-proxy to bridge stdio ↔ HTTP. Claude Code connects natively.

Claude Desktop — Settings → Developer → Edit Config:

{
  "mcpServers": {
    "statcan": {
      "command": "uvx",
      "args": ["mcp-proxy", "--transport", "streamablehttp", "http://localhost:8000/mcp"]
    }
  }
}

Claude Code

claude mcp add statcan --transport http http://localhost:8000/mcp --scope global

Cursor — .cursor/mcp.json or ~/.cursor/mcp.json:

{
  "mcpServers": {
    "statcan": {
      "command": "uvx",
      "args": ["mcp-proxy", "--transport", "streamablehttp", "http://localhost:8000/mcp"]
    }
  }
}

VS Code (GitHub Copilot) — .vscode/mcp.json:

{
  "servers": {
    "statcan": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-proxy", "--transport", "streamablehttp", "http://localhost:8000/mcp"]
    }
  }
}

Google Gemini (Antigravity) — ~/.gemini/antigravity/mcp_config.json:

{
  "mcpServers": {
    "statcan": {
      "command": "uvx",
      "args": ["mcp-proxy", "--transport", "streamablehttp", "http://localhost:8000/mcp"]
    }
  }
}

Full local / stdio (Option 3)

Claude Desktop — Settings → Developer → Edit Config:

{
  "mcpServers": {
    "statcan": {
      "command": "uvx",
      "args": ["statcan-mcp-server", "--db-path", "/Users/<you>/.statcan-mcp/statcan_data.db"]
    }
  }
}

Pass --db-path with an absolute path. Claude Desktop overrides the subprocess HOME env var, which breaks the default path resolution.

Claude Code

claude mcp add statcan --scope global -- uvx statcan-mcp-server

Cursor — .cursor/mcp.json or ~/.cursor/mcp.json:

{
  "mcpServers": {
    "statcan": {
      "command": "uvx",
      "args": ["statcan-mcp-server"]
    }
  }
}

VS Code (GitHub Copilot) — .vscode/mcp.json:

{
  "servers": {
    "statcan": {
      "type": "stdio",
      "command": "uvx",
      "args": ["statcan-mcp-server"]
    }
  }
}

Google Gemini (Antigravity) — ~/.gemini/antigravity/mcp_config.json:

{
  "mcpServers": {
    "statcan": {
      "command": "uvx",
      "args": ["statcan-mcp-server"]
    }
  }
}

Examples

Chat examples

Dashboard examples

Features & Tools

SDMX Tools — server-side filtered data fetch

Only the slice you request is returned. No downloading full tables.

Key syntax (passed to get_sdmx_data):

• "1.2.1" — Geography=1, Gender=2, Age=1
• ".2.1" — all geographies (wildcard), Gender=2, Age=1
• "1+2.2.1" — Geography 1 or 2, Gender=2, Age=1

Note: Wildcard (.) on dimensions with >30 codes returns a sparse, unpredictable sample — not all values. Use get_sdmx_key_for_dimension to get the correct OR key instead.

WDS Discovery & Metadata

WDS Series Resolution

WDS Change Detection

Composite & Database Tools (local/stdio mode only)

Typical workflow

1. search_cubes_by_title("unemployment rate")
   → productId e.g. 14100287

2. get_sdmx_structure(productId=14100287)
   → see dimension positions + sample codes

3. get_sdmx_key_for_dimension(productId=14100287, dimension_position=3)
   → or_key = "1+2+3+..." for large dimensions

4. get_sdmx_data(productId=14100287, key=".2.1", lastNObservations=24)
   → last 24 months, all geographies, seasonally adjusted

Project Structure

src/
├── api/
│   ├── cube/
│   │   ├── discovery.py         # search_cubes_by_title, get_all_cubes_list
│   │   ├── metadata.py          # get_cube_metadata
│   │   └── series.py            # get_series_info, change detection
│   ├── vector/
│   │   └── vector_tools.py      # vector series, bulk range fetch
│   ├── sdmx/
│   │   └── sdmx_tools.py        # get_sdmx_structure, get_sdmx_data, get_sdmx_key_for_dimension
│   ├── composite_tools.py       # fetch_vectors_to_database, store_cube_metadata
│   └── metadata_tools.py        # get_code_sets
├── db/                          # SQLite connection, schema, queries
├── models/                      # Pydantic input models
├── util/
│   ├── registry.py              # ToolRegistry — @decorator → MCP Tool schema
│   ├── truncation.py            # Response truncation + pagination guidance
│   ├── sdmx_json.py             # SDMX-JSON → tabular rows
│   └── cache.py                 # 1-hour TTL cache for cube list
├── config.py                    # BASE_URL, SDMX_BASE_URL, DB_FILE, TRANSPORT, PORT
└── server.py                    # create_server(), MCP Prompts, HTTP routes, CLI

Known Issues