Google Images (via Apify)

io.github.retracnv1.0.0Updated Oct 5, 2026

Google Images for AI agents: full-size image URLs, sizes and source pages, with filters.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingMedia & Design

Overview

AI-generated overview

Lets an assistant search Google Images through Apify and return full-size image URLs, dimensions, thumbnails and source pages.

What it does
This remote MCP server exposes an Apify actor that runs Google Images searches and returns one row per image: full-size image URL, width, height, file size, thumbnail, title, page URL and site. It supports filters for size, color, type (photo, clip art, line drawing, face, animated), time and usage rights, and is described as returning 100 images per search in seconds.
When to use it
Use it when an assistant needs image search results as structured data, for example gathering candidate images for a design or content task, or collecting image metadata and source pages. It is not a general web search tool; it is specifically for Google Images results.
Requirements
A remote MCP endpoint at mcp.apify.com, reachable over the network. It requires an Apify API token sent in the Authorization header as a Bearer token; a free Apify account provides one. Usage is billed per image, with a free monthly credit mentioned.
Before you install
The Authorization header carries an Apify API token, so treat it as a secret. The service is paid per image, so searches consume account credit. Returned image URLs and source pages point to third-party sites, and licensing must be checked on the source page before reuse.

Installation

In SourceWeft

  1. Open Google Images (via Apify) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "google-images": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=automationnation/google-images-scraper"
    }
  }
}

README

Google Images Scraper & API: full-size image URLs

[Run on Apify]

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/

Quick facts

  • One row per image: full-size URL, width, height, file size, thumbnail, title, page URL and site.
  • Filters: size, color, type (photo, clip art, line drawing, face, animated), time and usage rights.
  • 100 images per search in seconds, plain HTTP.
  • Price: $0.25 per 1,000 images; the free $5 monthly credit covers 20,000 images.

Example input

json
{  "queries": [    "modern kitchen"  ],  "maxResultsPerQuery": 100}

Run it from code

REST API

bash
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

python
# pip install apify-clientfrom 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

js
// npm install apify-clientimport { 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);

Use it with AI agents (MCP)

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:

json
{  "mcpServers": {    "google-images-scraper": {      "command": "npx",      "args": [        "-y",        "@apify/actors-mcp-server",        "--tools",        "automationnation/google-images-scraper"      ],      "env": {        "APIFY_TOKEN": "YOUR_APIFY_TOKEN"      }    }  }}

FAQ

Is there a Google Images API? Google's Custom Search JSON API can search images but caps at 100 queries a day free and $5 per 1,000 after, with limited filters. Google Images Scraper on Apify returns the full results page 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.

More from AutomationNation

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.

Source: README.md at commit 5fa5a2c

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 5, 2026