Statistics Canada MCP Server

MCP server and CLI for Statistics Canada's Web Data Service (WDS) and SDMX REST API. Gives any MCP client — Claude, Cursor, VS Code Copilot, Gemini — structured access to Canadian statistical data. Includes a standalone statcan CLI for direct downloads without an LLM.

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.

• Quick Start
• Setup by Client
• How Claude.ai Uses This Server
• MCP Prompts
• statcan CLI
• Examples
• Features & Tools
• Project Structure
• Known Issues

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

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

Claude Desktop / Claude.ai

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

Claude Code

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

The hosted server provides all WDS + SDMX tools. Database tools (SQLite) require local setup (Option 3) — they are intentionally excluded from the shared server.

Run a local server with the same tools as the hosted version.

Step 1 — Install uv:

# 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:

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

Step 3 — Connect your client to http://localhost:8000/mcp.

Everything from Option 2, plus database tools for storing and querying data with SQL. Runs via stdio.

Step 1 — Install uv (same as above).

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

uvx downloads and runs the server automatically on first use.

Download StatCan data directly from the terminal. See statcan CLI.

uvx statcan-mcp-server        # installs the package
statcan search "labour force"
statcan download 14-10-0287-01 --last 12 --output lfs.csv

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"
    }
  }
}

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 / VS Code / Gemini — same mcp-proxy wrapper, pointing to http://localhost:8000/mcp.

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 can break default path resolution.

Claude Code

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

Cursor / VS Code / Gemini — use uvx statcan-mcp-server as the stdio command.

Claude.ai (web) has no bash sandbox — it can't run shell commands. Instead, it uses MCP tools for discovery and its Python script tool to fetch data without bloating the context window.

The pattern:

1. MCP tools (small payloads — metadata only):
   search_cubes_by_title("labour force")  → productId
   get_sdmx_structure(productId=...)      → dimension layout + codes
   get_sdmx_key_for_dimension(...)        → OR key for large dimensions

2. Python script (data never enters context):
   url = "https://mcp-statcan.onrender.com/files/sdmx/<pid>/<key>?lastNObservations=12"
   → fetch → write to /tmp/statcan_<pid>.csv → print summary only

3. Follow-up script (analysis from /tmp/):
   rows = list(csv.DictReader(open("/tmp/statcan_<pid>.csv")))
   → filter / sort / aggregate → print only the result

get_sdmx_data on the hosted server always returns a download_csv URL instead of inline data — data stays out of the context window regardless of response size.

Claude Code (bash sandbox) uses the statcan CLI instead:

statcan search "labour force"
statcan download 14-10-0287-01 --last 12 --output /tmp/lfs.csv
awk -F',' 'NR>1 && $1=="Canada"' /tmp/lfs.csv | sort -t',' -rn -k5 | head -10

The server ships five prompts accessible as slash commands in supported clients. Each has dual instructions — Claude Code (bash) and Claude.ai web (Python script).

Usage in Claude Code:

/statcan-data-lookup topic="consumer price index" analysis_goal="trend last 5 years"
/statcan-download product_id=18100004 last_n=24

A standalone CLI for downloading StatCan data without an LLM. Outputs pipe-friendly CSV/JSON to stdout; progress and errors go to stderr.

Install:

pip install statcan-mcp-server   # or: uvx statcan-mcp-server (no install)

Commands:

statcan search <term>            Search tables by keyword
statcan metadata <product-id>    Show table structure (dimensions + members)
statcan download <product-id>    Download observations via SDMX
statcan vector <vector-id>...    Download one or more vector series
statcan codeset                  Show StatCan code definitions (UOM, frequency, etc.)

Common usage:

# Find a table
statcan search "consumer price index"
statcan search "labour force" --max-results 10 --format json

# Inspect structure before downloading
statcan metadata 18-10-0004-01
statcan metadata 18100004 --full        # show all dimension members

# Download data
statcan download 18-10-0004-01 --last 12 --output cpi.csv
statcan download 18-10-0004-01 --key "1.1.1" --start 2020-01 --end 2024-12
statcan download 18-10-0004-01 --last 5 --dry-run   # preview SDMX URL

# Download by vector ID
statcan vector v41690973 --last 24 --output series.csv
statcan vector v41690973 v41690974 --last 12 --output multi.csv

# Decode numeric codes
statcan codeset --type uom
statcan codeset --type frequency --format json

Output formats: csv (default for download/vector), table (default for search/metadata/codeset), json

Pipe patterns:

# Top 10 by value
statcan download 14-10-0287-01 --last 1 --format csv \
  | awk -F',' 'NR>1' | sort -t',' -k5 -rn | head -10

# Extract unique geographies
statcan download 14-10-0287-01 --last 1 --format csv \
  | awk -F',' 'NR>1 {print $1}' | sort -u

# Chain search → download
PID=$(statcan search "CPI" --format json | python3 -c "import sys,json; print(json.load(sys.stdin)[0]['Product ID'])")
statcan download $PID --last 12 --output cpi.csv

For the complete CLI reference see cli.md.

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. Use get_sdmx_key_for_dimension to get the correct OR key.

These tools are not available on the hosted Render server — SQLite is per-process and not shared across users.

Claude.ai web (hosted server):

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

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

3. get_sdmx_key_for_dimension(productId=14100287, dimension_position=3)
   → or_key for large dimensions

4. get_sdmx_data(productId=14100287, key=".2.1", lastNObservations=24)
   → returns download_csv URL

5. Python script: fetch URL → /tmp/statcan_14100287.csv → analyze → print summary

Claude Code (bash sandbox):

statcan search "unemployment rate"
statcan metadata 14100287
statcan download 14-10-0287-01 --last 24 --output /tmp/lfs.csv
awk -F',' 'NR>1 && $1=="Canada"' /tmp/lfs.csv | sort -t',' -rn -k5 | head -10

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 (stdio only)
│   └── metadata_tools.py        # get_code_sets
├── cli/
│   ├── main.py                  # statcan CLI entry point (Typer app)
│   ├── output.py                # write_output, format helpers
│   └── commands/
│       ├── search.py            # statcan search
│       ├── metadata.py          # statcan metadata
│       ├── download.py          # statcan download
│       ├── vector.py            # statcan vector
│       └── codeset.py           # statcan codeset
├── db/                          # SQLite connection, schema, queries (stdio only)
├── 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, RENDER_BASE_URL, TRANSPORT, PORT
└── server.py                    # create_server(), MCP Prompts, HTTP routes (/files/sdmx/), CLI