Google Images for AI agents: full-size image URLs, sizes and source pages, with filters.
One address for any MCP client. Your key stays in your Odel vault.
Not assessed yet.
Odel charges nothing per call. The publisher may charge for its own service.
| Access to | Read | Change |
|---|---|---|
| Full api access | Not stated: full_api_access | |
From the sign-in at console-backend.apify.com, as the endpoint publishes it. You approve it there.
Odel could not list its tools without signing in.
Google Images Scraper is an Apify Actor that returns Google Images results for any search: the full-size image URL, width, height and file size, thumbnail, title, source page and site, with filters for size, color, type, time and Creative Commons license, 100 images per search in seconds, at $0.25 per 1,000 images.
Price: $0.25 per 1,000 images ($0.20 on Gold and above) · Run it: https://apify.com/automationnation/google-images-scraper · Guide: https://retracn.github.io/automationnation-actors/google-images-scraper/
{
"queries": [
"modern kitchen"
],
"maxResultsPerQuery": 100
}
REST API
curl -X POST "https://api.apify.com/v2/acts/automationnation~google-images-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
-H "Content-Type: application/json" \
-d '{"queries": ["modern kitchen"], "maxResultsPerQuery": 100}'
Python — see examples/python_example.py
# pip install apify-client
from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("automationnation/google-images-scraper").call(run_input={
"queries": [
"modern kitchen"
],
"maxResultsPerQuery": 100
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item.get("title"), item.get("imageUrl"), item.get("imageWidth"), item.get("pageUrl"))
JavaScript — see examples/node_example.mjs
// npm install apify-client
import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('automationnation/google-images-scraper').call({
"queries": [
"modern kitchen"
],
"maxResultsPerQuery": 100
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
for (const item of items) console.log(item.title, item.imageUrl, item.imageWidth, item.pageUrl);
Hosted MCP server URL (Claude, ChatGPT, Cursor and other clients with remote MCP support):
https://mcp.apify.com?tools=automationnation/google-images-scraper
Local config for Claude Desktop / Cursor — mcp/claude_desktop_config.json:
{
"mcpServers": {
"google-images-scraper": {
"command": "npx",
"args": [
"-y",
"@apify/actors-mcp-server",
"--tools",
"automationnation/google-images-scraper"
],
"env": {
"APIFY_TOKEN": "YOUR_APIFY_TOKEN"
}
}
}
}
Is there a Google Images API? Google's Custom Search JSON API is closed to new customers and retires on 1 January 2027, and it returned only 10 images per request. Google Images Scraper on Apify returns up to 100 images per search as data, pay per image.
Can I filter for Creative Commons images? Yes: set Usage rights to Creative Commons. Always check the license on the source page.
This repository holds usage examples. The scraper itself runs on the Apify platform; you need a free Apify account and API token. Examples are MIT licensed.