ontario-data-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ontario-data-mcpfind datasets about traffic accidents in Toronto"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ontario-data-mcp
Beta: This project is under active development. The data structure and tool interfaces may change.
LLM-generated analysis may contain errors. Always verify critical findings against the returned source data.
This is an MCP server for discovering, downloading, querying, and analyzing datasets from Ontario's Open Data portals. It allows asking questions of the data in English (or Spanish, Chinese, French, etc).
It currently supports the Ontario, Toronto, Ottawa, Waterloo, Kitchener, and Region of Waterloo portals, and utilizes a shared DuckDB cache for fast SQL queries, statistical analysis, and geospatial operations.
Contributing
Contributions welcome! To get started, see Installation below.
Found a bug? Have an idea? Discovered something interesting? Open an issue here: https://github.com/sprine/ontario-data-mcp/issues
Features
find- search across supported Ontario open data portalsdownload- retrieve and cache datasetsquery- run SQL, statistical, and geospatial analysis via DuckDBvalidate— verify that data claims are supported by query resultsA shared DuckDB cache for high-performance analytics
Architecture
flowchart TD
Client["AI Client<br/>(Claude Code · VS Code · etc.)"]
subgraph Server["ontario-data-mcp (FastMCP)"]
direction TB
subgraph Tools["MCP Tools"]
direction LR
T1["Discovery"]
T2["Metadata"]
T3["Retrieval"]
T4["Querying"]
T5["Geospatial"]
T6["Quality & Validation"]
end
PC["Portal Clients<br/>CKANClient · ArcGISHubClient"]
Cache[("DuckDB Cache<br/>~/.cache/ontario-data/")]
Tools -->|"fan out to all portals"| PC
T3 & T5 -->|"download → store"| Cache
T4 & T6 -->|"SQL queries"| Cache
end
subgraph Portals["Open Data Portals"]
direction LR
CKAN["Ontario · Toronto<br/>CKAN API"]
ArcGIS["Ottawa · Waterloo · Kitchener<br/>Region of Waterloo<br/>ArcGIS Hub"]
end
Client <-->|"MCP Protocol"| Tools
PC -->|"CKAN 2.8"| CKAN
PC -->|"OGC Records / Hub v3"| ArcGISData flow: Discovery and metadata tools fan out to all portals in parallel. Retrieval tools download data and store it in a local DuckDB cache. Querying and quality tools run fast SQL locally against the cache — no repeated API calls.
Installation
With Claude Code
claude mcp add ontario-data -- uvx ontario-data-mcpTo auto-approve all tool calls (no confirmation prompts), add to your Claude Code settings:
{
"permissions": {
"allow": ["mcp:ontario-data:*"]
}
}Tools are annotated as read-only or destructive per the MCP spec. Download tools populate the local cache but are read-only (no remote mutations). Destructive tools (cache_manage, refresh_cache) only modify local cached data.
Add to .vscode/mcp.json:
{
"mcpServers": {
"ontario-data": {
"command": "uvx",
"args": ["ontario-data-mcp"]
}
}
}git clone https://github.com/sprine/ontario-data-mcp
cd ontario-data-mcp
uv sync
uv run ontario-data-mcpTo connect from source to Claude Code:
Note: MCP subprocesses don't inherit your shell's PATH, so you must use the absolute path to
uv(find it withwhich uv).
claude mcp add ontario-data -- /absolute/path/to/uv run --directory /path/to/ontario-data-mcp ontario-data-mcpSupported Portals
All searches fan out to every portal by default — no need to select a portal. Dataset and resource IDs are prefixed with their portal (e.g. toronto:abc123).
Portal | Platform | Datasets |
| CKAN | ~5,700 |
| CKAN | ~533 |
| ArcGIS Hub | ~665 |
| ArcGIS Hub | ~129 |
| ArcGIS Hub | ~219 |
| ArcGIS Hub | ~125 |
List of tools available to the AI agent
Tool | Description |
| Search for datasets across all portals (or narrow with |
| List all available portals with platform type |
| List government ministries with dataset counts |
| List all tags/topics in the catalogue |
| Find datasets related by tags and organization |
Tool | Description |
| Get full metadata for a dataset (use prefixed ID like |
| List all files in a dataset with formats and sizes |
| Get column schema and sample values for a datastore resource |
| Compare metadata side-by-side for multiple datasets (cross-portal) |
Tool | Description |
| Download a resource and cache it in DuckDB (use prefixed ID like |
| Cache statistics + list all cached datasets with staleness |
| Remove a single cached resource or clear the entire cache |
| Re-download cached resources with latest data |
Tool | Description |
| Query a resource via CKAN Datastore API (remote) |
| Run SQL against the CKAN Datastore (remote) |
| Run SQL against locally cached data in DuckDB |
| Quick preview of first N rows of a resource |
Tool | Description |
| Check if a dataset is current vs. its update schedule |
| Statistical profile using DuckDB SUMMARIZE |
| Validate that a data claim is supported by query results |
Tool | Description |
| Cache a geospatial resource (SHP, KML, GeoJSON) into DuckDB |
| Run spatial queries against cached geospatial data |
| Find datasets containing geospatial resources |
MCP Resources
Resources the agent can read for context without calling a tool:
URI | Description |
| List of all locally cached datasets with freshness info |
| Full metadata for a specific dataset (supports prefixed IDs) |
| Overview statistics across all data portals |
| Column schema, types, sample values, and type warnings for a cached table |
| DuckDB SQL reference for Ontario open data analysis |
Prompts
Context-aware guided workflow prompts:
explore_topic— Guided exploration of a topic (fetches live catalogue context)data_investigation— Deep dive into a specific dataset: schema, quality, statisticscompare_data— Side-by-side analysis of multiple datasets
Environment Variables
Variable | Default | Purpose |
|
| DuckDB storage + log file location |
|
| HTTP timeout in seconds |
|
| Max CKAN requests per second |
Development
uv sync
uv run python -m pytest tests/ -vLicense
MIT — see LICENSE for the software.
Data accessed through this tool is provided under the following open government licences:
Contains information licensed under the Open Government Licence – Ontario.
Contains information licensed under the Open Government Licence – Toronto.
Contains information licensed under the Open Government Licence – City of Ottawa.
Contains information licensed under the City of Waterloo Open Data Licence.
Contains information licensed under the Open Government Licence - The Corporation of the City of Kitchener.
Contains information licensed under the Region of Waterloo Open Data Licence v.2.0.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sprine/ontario-data-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server