mcp-canada
MCP server giving AI agents structured access to Canadian federal, provincial, and municipal government data.
README
<p align="center"> <h1 align="center">π mcp-canada</h1> <p align="center"> <strong>MCP server giving AI agents structured access to Canadian federal, provincial, and municipal government data</strong> </p> <p align="center"> <a href="https://pypi.org/project/mcp-canada/"><img src="https://img.shields.io/pypi/v/mcp-canada?color=blue&label=PyPI" alt="PyPI"></a> <a href="https://pypi.org/project/mcp-canada/"><img src="https://img.shields.io/pypi/dm/mcp-canada?color=blue&label=downloads" alt="PyPI downloads"></a> <a href="https://github.com/ReyemTech/mcp-canada/actions/workflows/ci.yml"><img src="https://github.com/ReyemTech/mcp-canada/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://github.com/ReyemTech/mcp-canada/actions/workflows/ci.yml"><img src="https://img.shields.io/badge/coverage-96%25-brightgreen" alt="Coverage 96%"></a> <a href="https://github.com/ReyemTech/mcp-canada/stargazers"><img src="https://img.shields.io/github/stars/ReyemTech/mcp-canada?style=flat&logo=github" alt="GitHub stars"></a> <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.12+-blue" alt="Python 3.12+"></a> <a href="https://github.com/ReyemTech/mcp-canada/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="License: MIT"></a> <a href="https://modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP-compatible-purple" alt="MCP Compatible"></a> <a href="https://github.com/jlowin/fastmcp"><img src="https://img.shields.io/badge/built%20with-FastMCP-orange" alt="Built with FastMCP"></a> </p> </p>
217 tools, ~87 prompts, and ~117 resources across 9 federal APIs + 5 provincial APIs + 2 municipal APIs + 1 local SQLite datastore β exchange rates, parliamentary data, product recalls, drug information, 80K+ open datasets, food nutrition data, real-time weather, immigration statistics, Ontario provincial data, Toronto municipal data, York Region ArcGIS Hub data, British Columbia CKAN + WFS geospatial data, Quebec DonnΓ©es QuΓ©bec CKAN + ArcGIS IQA data, Alberta open data + AER energy + WMBappServices wildfire + AHSGIS health + 511 Alberta transport, and persistent local storage. All bilingual (English/French).
First ArcGIS Hub module β shared infrastructure in
shared/arcgis_hub.pyis reusable for future Canadian municipal modules (BC, Calgary, Edmonton, and other cities publishing via ArcGIS Hub). First OGC WFS module β BC introduces WFS 2.0 (OGC) support viashared/ogc.py, making WFS the third portal technology alongside CKAN and ArcGIS Hub. Seedocs://bc/wfs-query-guidefor the CKANβWFS two-step workflow.
Quick Start
# Auto-configure your platform (interactive)
uvx mcp-canada install
# Or name platforms directly
uvx mcp-canada install claude-desktop cursor vscode
Supports 14 platforms: Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, Codex CLI, Gemini CLI, Amazon Q, OpenCode, Cline, Roo Code, Goose CLI, Junie CLI.
Manual Setup
<details> <summary>Claude Desktop</summary>
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"mcp-canada": {
"command": "uvx",
"args": ["mcp-canada"]
}
}
}
</details>
<details> <summary>Claude Code</summary>
claude mcp add mcp-canada -- uvx mcp-canada
</details>
<details> <summary>From Source</summary>
git clone https://github.com/reyemtech/mcp-canada.git
cd mcp-canada
uv run mcp-canada
</details>
Options
| Flag | Description | Example |
|---|---|---|
--transport |
Transport protocol | --transport sse |
--port |
Port for SSE/HTTP | --port 8000 |
--modules |
Load only specific modules | --modules bank_of_canada,recalls |
--verbose |
INFO-level logging | --verbose |
--debug |
DEBUG-level logging | --debug |
Environment variable: MCP_CANADA_MODULES=bank_of_canada,recalls
Examples
See EXAMPLES.md for 23 cross-API intelligence scenarios β from tracing prairie drought to the Canadian dollar, to building pharmaceutical safety audits, to assembling MP accountability briefs, to joining data from multiple APIs in a single SQL query. Each example includes the exact prompt and tool chain you can run today.
How Discovery Works
With 217 tools, listing all of them would consume half an agent's context window. Instead, BM25 search lets agents find exactly what they need:
Agent: "What tools do you have for exchange rates?"
β discover_tools("exchange rate CAD")
β Returns: boc_get_exchange_rates, boc_get_observations
β call_tool("boc_get_exchange_rates", {"currency": "USD", "recent": 3})
β Returns: {"_meta": {...}, "data": [{"date": "2026-04-02", "value": 1.3918, ...}]}
Agents see 5 always-visible tools:
| Tool | Purpose |
|---|---|
discover_tools |
BM25 natural language search across all tools |
call_tool |
Execute any discovered tool by name |
list_modules |
List available API modules with tool counts |
plan_query |
Plan a multi-step query across Canadian government data APIs |
execute_batch |
Run multiple tool calls in parallel with per-step error isolation |
Modules
All tools accept lang: "en" | "fr" for bilingual support. Responses include a _meta envelope with source attribution and cache status. Click a module for its full tool, prompt, and resource catalog.
| Module | Level | Tools | Prompts | Resources | Description |
|---|---|---|---|---|---|
| Meta / Discovery | β | 5 | β | β | Always-visible orchestration tools (discover_tools, call_tool, list_modules, plan_query, execute_batch) |
| Bank of Canada | Federal | 8 | 5 | 7 | Exchange rates, interest rates, commodity prices, inflation β Valet API |
| CKAN Open Data | Federal | 7 | 5 | 7 | 80,000+ federal datasets β open.canada.ca |
| Drug Database | Federal | 8 | 5 | 7 | Drug products, ingredients, schedules β Health Canada DPD |
| IRCC Immigration | Federal | 10 | 5 | 7 | PR, study/work permits, Express Entry, asylum β IRCC Open Data |
| Nutrient File | Federal | 8 | 5 | 7 | Food nutrition data β Canadian Nutrient File |
| Open Parliament | Federal | 10 | 5 | 7 | Bills, MPs, votes, ballots, Hansard debates β Open Parliament API |
| Recalls & Safety | Federal | 6 | 4 | 6 | Food, vehicle, and health product recalls β Healthy Canadians |
| Statistics Canada | Federal | 15 | 6 | 8 | Time series, cube metadata, SDMX filtering β StatCan WDS |
| Weather | Federal | 34 | 6 | 8 | Conditions, climate, air quality, hydrology, marine, radar β MSC GeoMet |
| Alberta | Provincial | 24 | 6 | 7 | CKAN + AER energy + WMBappServices wildfire + AHSGIS health + 511 Alberta β open.alberta.ca |
| British Columbia | Provincial | 20 | 6 | 7 | CKAN + WFS geospatial β BC Data Catalogue |
| Ontario | Provincial | 6 | 4 | 6 | 3,000+ provincial datasets β Ontario Open Data |
| Quebec | Provincial | 18 | 6 | 7 | Federated CKAN (139 orgs) β DonnΓ©es QuΓ©bec |
| Toronto | Municipal | 12 | 6 | 8 | TTC, neighbourhoods, 311, RentSafe β Toronto Open Data |
| York Region | Municipal | 27 | 5 | 8 | 4 ArcGIS Hub portals (York Region, Markham, Newmarket, Aurora) |
| Local Datastore | Local | 6 | 4 | 6 | SQLite persistence for cross-API SQL JOINs β ~/.mcp-canada/datastore.db |
| Total | 217 | ~87 | ~117 |
Response Format
All tools return a consistent envelope:
{
"_meta": {
"source": {"api": "bank-of-canada-valet", "url": "https://..."},
"cached": true,
"lang": "en",
"timestamp": "2026-04-04T12:00:00Z"
},
"data": [ ... ]
}
Errors return:
{
"error": {
"code": "INVALID_SERIES",
"message": "Series 'FXXYZCAD' not found.",
"suggestions": ["FXUSDCAD", "FXEURCAD"]
}
}
Architecture
src/mcp_canada/
βββ server.py # FastMCP entry point, transport, module loading
βββ shared/ # Cross-module utilities
β βββ cache.py # TTL-based in-memory cache (aiocache)
β βββ envelope.py # Response/error envelope (make_response/make_error)
β βββ http.py # Shared HTTP client with retry (tenacity)
β βββ rate_limiter.py # Per-source token bucket
β βββ i18n.py # Bilingual error messages
βββ meta/
β βββ list_modules.py # list_modules meta-tool
βββ modules/
βββ bank_of_canada/ # 8 tools β Valet API
βββ open_parliament/ # 10 tools β Parliament API
βββ recalls/ # 6 tools β Healthy Canadians API
βββ drug_database/ # 8 tools β Health Canada DPD
βββ ckan/ # 7 tools β Open Data Portal
βββ nutrient_file/ # 8 tools β Canadian Nutrient File
βββ datastore/ # 6 tools β local SQLite persistence
βββ ircc/ # 10 tools β IRCC Immigration Open Data
βββ ontario/ # 6 tools β Ontario Open Data Catalogue
βββ toronto/ # 12 tools β City of Toronto Open Data Portal
βββ york_region/ # 27 tools β York Region ArcGIS Hub (4 portals)
βββ british_columbia/ # 20 tools β BC Data Catalogue + WFS
βββ quebec/ # 18 tools β DonnΓ©es QuΓ©bec CKAN
βββ alberta/ # 24 tools β open.alberta.ca CKAN + AER + WMB + AHSGIS + 511
βββ statcan/ # 15 tools β Statistics Canada WDS + SDMX
βββ weather/ # 34 tools β MSC GeoMet OGC API
βββ current/ # 5 tools β realtime conditions, forecast, alerts
βββ climate/ # 7 tools β daily/monthly/normals/trends
βββ aqhi/ # 3 tools β air quality health index
βββ hydro/ # 5 tools β water levels, flow, flood risk
βββ marine/ # 3 tools β marine forecasts, hurricane tracks
βββ severe/ # 3 tools β radar, lightning, UV index
βββ snow/ # 2 tools β snow depth, snow water equivalent
βββ collections/ # 2 tools β collection browser and direct query
βββ summary/ # 4 tools β composite summary, extremes, growing season, degree days
Each module follows a 7-file pattern:
| File | Purpose |
|---|---|
__init__.py |
Module name and description |
constants.py |
Base URL, rate limits, cache TTLs, API mappings |
schemas.py |
Pydantic v2 response models (always flat) |
client.py |
Async HTTP functions with caching and rate limiting |
tools.py |
@tool decorated MCP tool functions |
prompts.py |
@prompt functions β guided workflows + quick lookups |
resources.py |
@resource functions β catalogs, docs, templates |
New modules are auto-discovered β drop a folder in modules/ and it registers via FileSystemProvider.
Development
# Install dependencies
uv sync
# Run tests (~2000 unit tests, ~15s)
uv run pytest
# Run integration tests against live APIs (~2min)
uv run pytest tests/integration/ -v -m integration --timeout=120
# Type check and lint
uv run pyright
uv run ruff check src/ tests/
# Coverage (must be β₯95%)
uv run pytest --cov=src/mcp_canada --cov-fail-under=95
Contributing
Each module is self-contained. To add a new API:
- Create
src/mcp_canada/modules/your_api/with the 7-file pattern - Add colocated
__tests__/with unit tests - Add integration tests in
tests/integration/test_tool_scenarios.py - Add a module doc in
docs/modules/and update the Modules table in this README
See CLAUDE.md for coding conventions.
Changelog
See CHANGELOG.md for version-by-version changes, or browse GitHub Releases.
Security
Found a vulnerability? Please do not open a public issue. Email contact@reyem.tech with details and reproduction steps. We support the latest minor version on PyPI.
Community
- Questions & ideas: GitHub Discussions
- Bugs & feature requests: GitHub Issues
- Contact: contact@reyem.tech
License
MIT β Reyem Tech
Star History
<a href="https://star-history.com/#ReyemTech/mcp-canada&Date"> <img src="https://api.star-history.com/svg?repos=ReyemTech/mcp-canada&type=Date" alt="Star History Chart"> </a>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.