How to Find Where to Buy an Item from an Image with OpenClaw
Find where to buy items from images with OpenClaw and ToolRouter. Batch visual product search.
Tool
OpenClaw processes visual product searches in batch, taking multiple image URLs and returning normalized product identification and purchase source data for shopping platforms, style discovery apps, or automated product cataloguing. Process large image sets without individual visual searches.
Connect ToolRouter to OpenClaw
1Install the CLI
npm install -g toolrouter-mcp2Call tools directly from OpenClaw
toolrouter-mcp call web-search search --query "AI tools"
toolrouter-mcp toolsSteps
Once connected (see setup above), use the Style Finder tool:
- Prepare a list of image URLs to process
- Ask: "Use style-finder with find_by_url to identify and find purchase options for each image URL"
- OpenClaw returns structured product and shopping data for each URL
- Normalize to a stable schema with product_type, style_keywords, purchase_sources, price, and url
Example Prompt
Try this with OpenClaw using the Style Finder tool
Use style-finder with find_by_url to process these 10 product image URLs and find purchase options for each. Return stable JSON with image_url, product_type, style_keywords, and purchase_sources including source_name, price, currency, buy_url, and in_stock.
Tips
- Lock the schema before processing large image batches so all results are directly comparable
- Include the source image_url as a key field so results can be matched back to input images
- Filter for in_stock entries before indexing in a shopping catalogue to keep results actionable