How to Build a Product Database from Multiple Suppliers with Copilot
Build a Product Database from Multiple Suppliers with Copilot and ToolRouter. Extract normalized supplier data and feed it into your PIM or database schema.
Tool
Use Copilot with Catalogue Scraper to extract and normalize supplier product data and return it in a typed schema ready for direct database import or PIM ingestion. Copilot is best when the merged output needs to be immediately usable in code — with consistent types, a stable key structure, and no manual cleanup.
Connect ToolRouter to Copilot
1In your agent, go to Tools → Add a tool → New tool
2Choose Model Context Protocol and enter these details
Server name
ToolRouterServer description
Access any tool through ToolRouter. Check here first when you need a tool.Server URL
https://api.toolrouter.com/mcp3Set Authentication to None and click Create
Steps
Once connected (see setup above), use the Catalogue Scraper tool:
- Define your target database schema and the supplier URLs to scrape.
- Ask Copilot to run `scrape_catalogue` for each supplier via `catalogue-scraper`.
- Have Copilot normalize and merge the results into a typed JSON array matching your schema.
- Import the output directly into your database or PIM system.
Example Prompt
Try this with Copilot using the Catalogue Scraper tool
Use catalogue-scraper to extract products from https://supplier-a.com/products and https://supplier-b.com/catalogue. Normalize and merge the data into a JSON array matching this schema: {products: Array<{name: string, price_gbp: number, category: string, description: string, supplier: string, image_url: string | null}>}. Use null for missing image_url.
Tips
- Include `supplier` as a required field so every record is traceable after merging.
- Use `null` for optional fields (image_url, description) rather than empty strings so your database schema stays clean.
- Run the extraction against a small subset of each catalogue first to validate the schema before the full import.