Health Canada Summary Reports MCP Server
Click on "Deploy 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., "@Health Canada Summary Reports MCP ServerWhy did Health Canada approve Ozempic?"
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.
Health Canada Summary Reports — MCP server
Server MCP that exposes Santé Canada's public "Summary Reports" API (Summary Basis of Decision / SBD, Regulatory Decisions / RDS, Summary Safety Reviews / SSR) as tools usable by an MCP-compatible agent — notably a Microsoft Copilot Studio agent.
Companion tool to health-canada-summary-reports-explorer (the web version), same source API, no data is stored or sent anywhere except health-products.canada.ca.
Exposed tools
searchHealthCanadaReports— search by product name, manufacturer, ingredient, therapeutic area, or control number. Returns a short list of matching IDs.getHealthCanadaReport— retrieves the full text of a report by its exact ID (formatted as Markdown).
Both tools accept reportType (sbd | rds | ssr) and lang (fr | en, default fr).
Related MCP server: Enterprise Knowledge MCP Server
Local setup
Prerequisites: Node.js 18+.
npm install
npm run build
npm startThe server listens on http://localhost:3000/mcp.
Connect the server to Copilot Studio
Copilot Studio must reach the server via a public HTTPS URL. For development/testing, the easiest way is to use Dev Tunnels (official Microsoft tool):
devtunnel host -p 3000 --allow-anonymousCopy the generated URL (format https://xxxxx-3000.devtunnels.ms — the port is a suffix in the hostname, not :3000) and append /mcp to the end.
Then, in Copilot Studio:
Open your agent → Tools tab → Add a tool.
Select Model Context Protocol.
Fill in:
Server name:
Rapports sommaires Santé CanadaDescription:
Recherche et consultation des rapports de décision réglementaire et d'innocuité de Santé Canada (médicaments et instruments médicaux).Server URL:
https://xxxxx-3000.devtunnels.ms/mcpAuthentication:
Aucune(the source API is public, no key)
Click Create, then test in the Preview tab with a question like "Why did Santé Canada approve Abilify?" or "Has there been a safety review of tofacitinib?".
Production deployment
A development tunnel is not intended to remain open continuously. For permanent use, host this Node.js server on a standard platform (Azure Container Apps, Azure App Service, Render, Fly.io, etc.) and use its stable HTTPS URL instead of the devtunnel URL in Copilot Studio. The server requires no database or environment variables (except optionally PORT).
Structure
src/
├── index.ts # serveur MCP (transport Streamable HTTP sur /mcp)
├── api.ts # client de l'API Santé Canada + cache en mémoire des listes
└── format.ts # conversion des champs HTML de l'API en Markdown lisibleThis server cannot be deployed
Maintenance
Related MCP Connectors
Agentic search over your Dewey document collections from any MCP-compatible client.
Agent-driven search: build, import, tune, search, and score result quality — all over MCP.
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
- docs2mcpOAuthcom.docs2mcp
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceTransforms PDF collections into a searchable knowledge base using TF-IDF indexing and proximity matching. It enables users to search documents, retrieve specific page content, and manage document libraries through natural language via MCP clients.5-
- FlicenseNot gradedqualityCmaintenanceProvides read-only, citation-backed semantic search and retrieval-augmented generation over enterprise documents via standardized MCP tools, with local embeddings for privacy.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query and manage a document knowledge base via MCP, with RAG-powered search and grounded answers with citations.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to securely search and ingest corporate documents via MCP, offering hybrid retrieval, PII sanitization, role-based access control, and citation validation.MIT