Google Lens Visual Search From Claude via MCP
Point Claude at Google Lens style visual search through MCP: send an image URL mid-chat, get matches with title, source and url back as structured JSON.
Input
Output fields
Sign up on Apify or log in
The Google Lens API | Reverse Image and Visual Product Search Actor is ready to run with the inputs already set for "Google Lens Visual Search From Claude via MCP". Sign up or log in and you'll land in Apify Console with a copy of this exact task.
Start the "Google Lens Visual Search From Claude via MCP" task
The Google Lens API | Reverse Image and Visual Product Search Actor will start running based on the input automatically. You can also change all the input fields, like image url, search type, and more, to match your specific use case.
Receive the "Google Lens Visual Search From Claude via MCP" output
Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as title, source, price, and more.
Integrate into your workflow
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Google Lens Visual Search From Claude via MCP" task via API.

Integrate "Google Lens Visual Search From Claude via MCP" into your workflow
Connect "Google Lens Visual Search From Claude via MCP" with 100+ integrations, or run it via API or MCP.
Webhook
n8n
Make
Zapier
Airbyte
Keboola
IFTTT
Hubspot
GDrive
Gmail
Apify MCP
GitHub
Slack
LangChain
LlamaIndex
Flowise
Pinecone
OpenAI
Mastra
Clay
Each match is a row with title, source, url, thumbnail and image, and shoppable listings add price, currency and inStock where the retailer publishes them. Claude reads the rows straight from the dataset, or you export them as JSON, CSV or Excel.
An image_url such as https://i.imgur.com/HBrB8p0.png plus search_type and max_results 20. The example shows search_type products, which Google retired in October 2026, so use visual_matches: that mode now carries the shoppable listings.
Call the task's run endpoint on the Apify API or use apify-client for Python or Node with image_url as input, then read the dataset as JSON or CSV. MCP is the chat path; the API is the same lookup for scripts and backends.
Save the lookup as a task in the Apify Console, choose Actions, then Schedule, and set a cron such as 0 */6 * * * for every six hours. The dataset refreshes on its own, and a webhook or the Slack integration can post new matches as they land.
In Claude, add https://mcp.apify.com/?tools=actors,docs,johnvc/google-lens-api as an MCP server. Claude then sees the Google Lens API as a tool, asks for the image URL, runs the lookup and quotes title, source and price from the rows it gets back.
Pay per result, no setup fee, and a failed lookup is not charged. Every image is billed a minimum number of visual matches, so a tiny max_results saves nothing below that floor. The free tier and current rate are on the Actor page.
Google Lens Visual Search From Claude via MCP is not an official Google product; it reads public Lens results and hands them to Claude as JSON. For the same lookup inside a script rather than a chat, see Reverse Image Search in Python via API.