# Google Images API - $0.10 per 1,000 - Fast Image API (`johnvc/google-images-api`) Actor

Scrape Google Images at scale and export clean JSON: image URL, width and height, thumbnail, source site, domain, and the page link. Bulk image search for SEO research, training datasets, and AI agents. Pay per image from $0.10 per 1,000 results, with no setup or per-run fee.

- **URL**: https://apify.com/johnvc/google-images-api.md
- **Developed by:** [John](https://apify.com/johnvc) (community)
- **Categories:** SEO tools, Developer tools, MCP servers
- **Stats:** 223 total users, 134 monthly users, 100.0% runs succeeded, 5 bookmarks
- **User rating**: 5.00 out of 5 stars

## Pricing

from $0.10 / 1,000 image scrapeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Google Images API - $0.10 per 1,000 - Fast Image API

Scrape Google Images in bulk and get clean, structured JSON: the full-size image URL with width and height, a thumbnail, the source site and domain, the page the image appears on, and Google's reference URL. Search many queries at once and export thousands of images. Pay per image from **$0.10 per 1,000 results**, with no setup or per-run fee.

This is the fast, cheap option. It talks to a structured image search API instead of driving a slow, breakable headless browser, so it is quick and reliable, and it is **10x cheaper than the cheapest mainstream alternative**. If you need reverse-image search, visual de-duplication, or downloading the raw image files, this is not the tool, see the comparison below.

### What you get

One clean row per image:

- `title` of the image as shown on the results page
- `imageUrl` to the full-size file, plus `imageWidth` and `imageHeight`
- `thumbnailUrl` with `thumbnailWidth` and `thumbnailHeight`
- `source` site name and `domain`
- `link` to the page where the image appears
- `googleUrl` reference link, plus the `query` and `position` it was found at

### What you do NOT get

- Downloading or re-hosting the raw image files
- Reverse-image search (find where an image appears)
- Visual de-duplication or perceptual hashing
- EXIF metadata extraction or face/object detection

Need those? [hooli/google-images-scraper](https://apify.com/hooli/google-images-scraper?fpr=9n7kx3) is the deep-feature incumbent for reverse-image and bulk-download workflows. This Actor is the fast, cheap complement for everyone who just needs the image search data in bulk.

### How this compares

| Actor | Price per image | Per 1,000 images |
|---|---|---|
| **This Actor** | **$0.0001** | **$0.10** |
| [crawlerbros/google-images-scraper](https://apify.com/crawlerbros/google-images-scraper?fpr=9n7kx3) | $0.001 | $1.00 |
| [hooli/google-images-scraper](https://apify.com/hooli/google-images-scraper?fpr=9n7kx3) | $0.00125 to $0.0035 | $1.25 to $3.50 |
| [easyapi/google-images-scraper](https://apify.com/easyapi/google-images-scraper?fpr=9n7kx3) | $0.005 | $5.00 |

Rule of thumb: **bulk image search at the lowest price, MCP-ready -> this Actor; reverse-image search and raw file downloads -> [hooli/google-images-scraper](https://apify.com/hooli/google-images-scraper?fpr=9n7kx3).**

### Use cases

- Build large image datasets for computer-vision or AI training pipelines
- Pull product, brand, or competitor imagery for SEO and marketing research
- Source reference images for content, design, and moodboards at scale
- Feed an AI agent image results for a topic in one MCP call
- Monitor how a brand or product appears in image search over time

### 🔌 Integrations: Automate Google Images API Data Collection

A single run answers one question ("what images rank for vintage road bikes right now?"). The real value comes from running the Google Images API on a schedule, so fresh image results and rankings land in your stack automatically. See the full list of [Apify platform integrations](https://docs.apify.com/platform/integrations).

**Tasks and Schedules (the core recipe).** Save one [task](https://docs.apify.com/platform/actors/running/tasks) per thing you track (a product line, a brand, or a keyword watchlist), then attach a [schedule](https://docs.apify.com/platform/schedules) from the actor's Actions, then Schedule menu. Useful cron strings: `0 7 * * *` (daily 7 AM), `0 */6 * * *` (every 6 hours), `0 9 * * 1` (Mondays). One schedule can trigger many tasks at once, so a single daily job can refresh every query you care about.

**n8n.** This API ships an n8n community node (see the n8n integration section below). A four-step monitor: Schedule Trigger, then the Google Images API node, then a Filter on `domain` or `imageWidth`, then Slack or email.

**Make and Zapier.** The same pattern works no-code with [Make](https://docs.apify.com/platform/integrations/make) and [Zapier](https://docs.apify.com/platform/integrations/zapier): trigger on a schedule, run the actor, route the new image rows where you need them.

**Store the history (Supabase).** Send each run's rows into a table so an image ranking history builds up over time. No-code: the n8n Actor node, then a Supabase node. Or in Python (each row carries `query`, `position`, `title`, `imageUrl`, `imageWidth`, `imageHeight`, `source`, `domain`, and `link`):

```python
from apify_client import ApifyClient
from supabase import create_client

apify = ApifyClient("YOUR_APIFY_TOKEN")
supabase = create_client("YOUR_SUPABASE_URL", "YOUR_SUPABASE_KEY")

run = apify.actor("johnvc/google-images-api").call(run_input={
    "queries": ["golden retriever puppy", "eiffel tower at night"],
    "maxResultsPerQuery": 100,
    "gl": "us",
    "hl": "en",
})
rows = list(apify.dataset(run["defaultDatasetId"]).iterate_items())
supabase.table("image_results").upsert(rows).execute()
```

**MCP and AI agents.** Add the Google Images API as a tool in Claude or Cursor through the Apify MCP server so an agent can pull image results for any topic in one call (see the Use this API from Claude section below).

**Webhooks.** For anything custom, fire an [Apify webhook](https://docs.apify.com/platform/integrations/webhooks) on `ACTOR.RUN.SUCCEEDED` to push each run's dataset into your own service.

### Input

| Field | Type | Description |
|-------|------|-------------|
| `queries` | array of strings | One or more image search queries, e.g. `golden retriever puppy`. Each is searched independently. Required. |
| `maxResultsPerQuery` | integer | Images per query. Default 100. Values below 50 are raised to 50. |
| `gl` | string | Optional two-letter country code, e.g. `us`, `gb`, `de`. Default `us`. |
| `hl` | string | Optional two-letter language code, e.g. `en`, `es`, `de`. Default `en`. |

#### Example input

```json
{
  "queries": ["golden retriever puppy", "eiffel tower at night"],
  "maxResultsPerQuery": 100,
  "gl": "us",
  "hl": "en"
}
```

### Sample output

```json
{
  "query": "golden retriever puppy",
  "position": 1,
  "title": "Golden Retriever Puppy",
  "imageUrl": "https://images.example.com/products/57215/golden-retriever-puppy.jpg",
  "imageWidth": 1047,
  "imageHeight": 699,
  "thumbnailUrl": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9Gc...",
  "thumbnailWidth": 275,
  "thumbnailHeight": 183,
  "source": "Photowall",
  "domain": "www.photowall.com",
  "link": "https://www.photowall.com/us/golden-retriever-puppy-wallpaper",
  "googleUrl": "https://www.google.com/imgres?imgurl=..."
}
```

### Pricing

Pay-per-result: you are charged a flat **$0.0001 per image** returned, which is **$0.10 per 1,000 images**. No per-run fee, no setup fee, no monthly minimum. You only pay for the images you receive.

That is 10x below the cheapest mainstream alternative and up to 50x below the premium tiers, so bulk image search stops being a budget line.

### How to get started

1. Open [Google Images Scraper on the Apify Store](https://apify.com/johnvc/google-images-api?fpr=9n7kx3).
2. Enter one or more `queries`.
3. Set `maxResultsPerQuery` (and optionally `gl` / `hl`), then run the Actor.
4. Export the dataset as JSON, CSV, or Excel, or pull it from the API.

Prefer code? See [johnvc's GitHub for setup guides and code examples](https://github.com/johnisanerd/ApifyPublicData). For a ready-to-run Python and MCP quick-start, see the [Google Images API example repo](https://github.com/johnisanerd/Google-Images-API).

### Run from the API

```bash
curl -X POST "https://api.apify.com/v2/acts/johnvc~google-images-api/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"queries":["golden retriever puppy"],"maxResultsPerQuery":50,"gl":"us","hl":"en"}'
```

### 🔌 Use this API from Claude (MCP)

This Actor is compatible with the Model Context Protocol (MCP), so AI agents can call it as a tool. Add it through the hosted Apify MCP server using this Actor-specific URL:

https://mcp.apify.com/?tools=actors,docs,johnvc/google-images-api

If you run agents from [Claude Code](https://claude.ai/referral/uIlpa7nPLg) (free trial) or [Claude Cowork](https://claude.ai/referral/uIlpa7nPLg) (free trial), add the Apify MCP server and call this Actor directly with requests like "get me 100 image results for vintage road bikes."

Setup walkthrough:

https://www.youtube.com/watch?v=jREWahDGhJM

Apify MCP integration docs: https://docs.apify.com/platform/integrations/mcp

#### MCP setup, step by step

Visual setup guides for each client (source and more assets: [ApifyPublicData on GitHub](https://github.com/johnisanerd/ApifyPublicData)):

**[Claude Cowork Desktop](https://claude.ai/referral/uIlpa7nPLg)** (free trial)

![Apify MCP install screenshot for the Cowork desktop app](https://raw.githubusercontent.com/johnisanerd/ApifyPublicData/main/assets/guides/install_mcp_into_claude_desktop.png)

**[Claude Code](https://claude.ai/referral/uIlpa7nPLg)** (free trial)

![Apify MCP install screenshot for the Code CLI](https://raw.githubusercontent.com/johnisanerd/ApifyPublicData/main/assets/guides/install_mcp_into_claude_code.png)

**Claude (website)**

![Install in Claude website](https://raw.githubusercontent.com/johnisanerd/ApifyPublicData/main/assets/guides/install_mcp_into_claude_ai.png)

**Cursor**

![Install in Cursor](https://raw.githubusercontent.com/johnisanerd/ApifyPublicData/main/assets/guides/install_mcp_into_cursor.png)

**ChatGPT**

![Install in ChatGPT](https://raw.githubusercontent.com/johnisanerd/ApifyPublicData/main/assets/guides/install_mcp_into_ChatGPT.png)

### 💸 Pay per run with crypto (x402)

The Google Images API supports agentic payments via the [x402 protocol](https://docs.apify.com/platform/integrations/x402).
AI agents and MCP clients can pay for runs in USDC (on Base) with no Apify account or API token needed:
point your agent at the [Apify MCP server](https://mcp.apify.com/?tools=actors,docs,johnvc/google-images-api) and it can
discover, pay for, and run this Actor autonomously. Read the
[Apify x402 announcement](https://apify.com/change-log/pay-for-apify-actors-with-x402?fpr=9n7kx3) for details.

### 🔗 Related Tools

Building a visual search or image data pipeline? These tools from the same catalog pair well with bulk Google Images scraping:

- [Yandex Reverse Image Search API](https://apify.com/johnvc/yandex-reverse-image-search?fpr=9n7kx3): the reverse-image complement this API does not cover, find where a given image already appears online.
- [Google Shopping API](https://apify.com/johnvc/google-shopping-api-google-shopping-products-prices-deals?fpr=9n7kx3): product imagery with prices and sellers when you need shopping results rather than open-web images.
- [Naver Search API](https://apify.com/johnvc/naver-search-api?fpr=9n7kx3): image, web, news, and video results from Korea's Naver for the same research in another market.
- [Google Short Videos API](https://apify.com/johnvc/google-short-videos-api?fpr=9n7kx3): Shorts, Reels, and TikTok results when the visual media you want is video rather than still images.

Older alternatives such as [scrapestorm/google-images-scraper](https://apify.com/scrapestorm/google-images-scraper---cheapest-pay-per-results?fpr=9n7kx3) market themselves as the cheapest option, yet charge about $0.0035 per image (roughly 35x the per-image cost here), show no monthly active users, and have not been updated in months. This Google Images API is actively maintained, returns clean structured JSON, and is pay-per-result with no start fee.

### FAQ

#### Does it download the actual image files?

No. It returns each image's `imageUrl` and `thumbnailUrl`. Follow the link to fetch the file yourself.

#### Does it do reverse-image search?

No. For reverse-image lookups and bulk file downloads, use [hooli/google-images-scraper](https://apify.com/hooli/google-images-scraper?fpr=9n7kx3).

#### How many images per query?

Set `maxResultsPerQuery` (default 100; values below 50 are raised to 50). Results come in pages and a query stops early when it runs out of images, so you only pay for what exists.

#### Why did I get fewer results than I asked for?

`maxResultsPerQuery` is a ceiling, not a guarantee. Niche queries simply have fewer matching images.

#### Can I search many queries at once?

Yes. Pass multiple `queries`; each is searched independently and tagged with its source query in the output.

#### Can I localize results?

Yes. Set `gl` (country) and `hl` (language) to localize the image results.

#### Can I schedule the Google Images API?

Yes. Any run can be automated. Save a [task](https://docs.apify.com/platform/actors/running/tasks) with your queries, then attach a [schedule](https://docs.apify.com/platform/schedules) from the actor's Actions, then Schedule menu. Handy cron strings are `0 7 * * *` (daily at 7 AM), `0 */6 * * *` (every six hours), and `0 9 * * 1` (Mondays), and one schedule can trigger many tasks at once. See the Integrations section above for the full Tasks and Schedules recipe, and the [Apify schedules docs](https://docs.apify.com/platform/schedules).

#### Should I use the Google Images API or a web scraper?

Both, and this actor is both. A first-party image API is usually rate limited, quota bound, and missing fields, while a raw [web scraper](https://en.wikipedia.org/wiki/Web_scraping) returns messy HTML you have to parse yourself. This Google Images scraper gives you the clean, structured result of a purpose-built [API](https://en.wikipedia.org/wiki/API): call it yourself, pay per image, no quotas, and get the same JSON whether you run one query or thousands.

#### How much does it cost to scrape Google Images?

You pay per image returned, with no per-run or setup fee, so a small query costs a fraction of a cent and bulk Google Images scraping stays cheap and predictable. See the Pricing section above for the exact per-result rate.

#### Can I use the Google Images API programmatically?

Yes. The Apify API runs the actor, schedules it, and fetches datasets, and the `apify-client` package exists for both Node.js and Python. See the Run from the API section above, or the actor's [API tab](https://apify.com/johnvc/google-images-api/api?fpr=9n7kx3).

#### Can I use the Google Images API through an MCP server?

Yes. Add it as a tool in any MCP client (Claude, Cursor, and others) through the hosted [Apify MCP server](https://mcp.apify.com/) with the actor-specific URL `https://mcp.apify.com/?tools=actors,docs,johnvc/google-images-api`. In [Claude Code](https://claude.ai/referral/uIlpa7nPLg) (free trial) or [Claude Cowork](https://claude.ai/referral/uIlpa7nPLg) (free trial) your agent can then answer requests like "get me 100 image results for vintage road bikes." See the [Apify MCP docs](https://docs.apify.com/platform/integrations/mcp).

#### Can I integrate the Google Images API with other apps?

Yes. It connects to almost any cloud service through [Apify integrations](https://docs.apify.com/platform/integrations): [Make](https://docs.apify.com/platform/integrations/make), [Zapier](https://docs.apify.com/platform/integrations/zapier), [Slack](https://docs.apify.com/platform/integrations/slack), the n8n community node, and [webhooks](https://docs.apify.com/platform/integrations/webhooks) on `ACTOR.RUN.SUCCEEDED` for custom actions. See the Integrations section above for full recipes.

#### Does the API return AI-generated images?

It returns whatever appears in the live [Google Images](https://images.google.com/) results for your query, which can include AI-generated pictures when those rank. There is no separate flag for AI images, so filter on `domain` or `source` if you want to keep or drop specific sites.

#### Can the API get images for a location or place?

Yes, indirectly. Put the place in the query text (for example "eiffel tower at night" or "downtown austin skyline") and the API returns the image results Google shows for that phrase. It reads the image search results and does not run object or landmark recognition on the files themselves.

#### Is there a free Google Images API key?

There is no official free image search API key with meaningful quota. This actor is the practical alternative: no key to request, no quota tier, and you pay only for the images you receive. See the Pricing section above.

#### How else can I collect image and search data?

Pair this API with related tools in the same catalog: the [Yandex Reverse Image Search API](https://apify.com/johnvc/yandex-reverse-image-search?fpr=9n7kx3) for reverse-image lookups this API does not do, the [Naver Search API](https://apify.com/johnvc/naver-search-api?fpr=9n7kx3) for image and web results in Korea, and the [Google Shopping API](https://apify.com/johnvc/google-shopping-api-google-shopping-products-prices-deals?fpr=9n7kx3) for product imagery with prices.

***

### n8n integration

Available as an n8n community node, **[n8n-nodes-google-images-api](https://www.npmjs.com/package/n8n-nodes-google-images-api)**. In n8n: Settings, Community Nodes, install `n8n-nodes-google-images-api`, then use it in any workflow (it also works as an AI Agent tool).

***

### Featured Tasks

Ready-to-run examples that show this API solving a specific problem. Each opens its own setup so you can run it on your account in one click.

- [Get Google Images results without an API key](https://apify.com/johnvc/google-images-api/examples/get-google-images-results-without-an-api-key?fpr=9n7kx3) - Search Google Images with no API key or quota setup.
- [Download Google Images results to CSV](https://apify.com/johnvc/google-images-api/examples/download-google-images-results-to-csv?fpr=9n7kx3) - Export Google Images results to CSV in one run: image URL, width, height, thumbnail, source site, domain, and page link for every result, ready for sheets.
- [Run image SERP research in Claude via MCP](https://apify.com/johnvc/google-images-api/examples/run-image-serp-research-in-claude-via-mcp?fpr=9n7kx3) - Do Google Images SERP research inside Claude via MCP.
- [Build an image dataset for machine learning](https://apify.com/johnvc/google-images-api/examples/build-image-dataset-for-machine-learning?fpr=9n7kx3) - Build an image dataset from Google Images for machine learning.
- [Get Google Images results in Python](https://apify.com/johnvc/google-images-api/examples/get-google-images-results-in-python?fpr=9n7kx3) - Get Google Images results in Python by API for any keyword.
- [Pull Google Images into n8n by API](https://apify.com/johnvc/google-images-api/examples/pull-google-images-into-n8n?fpr=9n7kx3) - Pull Google Images results into n8n by API for any keyword.
- [Find high-resolution images by keyword](https://apify.com/johnvc/google-images-api/examples/find-high-resolution-images-by-keyword?fpr=9n7kx3) - Find high-resolution images on Google by keyword.
- [Track Google Images rankings for a keyword](https://apify.com/johnvc/google-images-api/examples/track-google-images-rankings?fpr=9n7kx3) - Track which images rank on Google for a keyword.
- [批量导出谷歌图片搜索结果(CSV)](https://apify.com/johnvc/google-images-api/examples/piliang-daochu-google-tupian-csv?fpr=9n7kx3) - 按关键词批量获取谷歌图片: 原图链接、宽高、缩略图、来源网站与页面链接, 导出 CSV/JSON。
- [为 AI 训练构建图片数据集(按关键词)](https://apify.com/johnvc/google-images-api/examples/ai-xunlian-tupian-shujuji?fpr=9n7kx3) - 按关键词批量收集谷歌图片的原图 URL 与尺寸, 快速搭建机器学习训练数据集。

***

### 🌐 About Alpha OSINT

This Actor is part of [Alpha OSINT](https://www.alphaosint.com), toolset of financial and operations data sources and APIs.
See the [Google Images API - $0.10 per 1,000 - Fast source page](https://www.alphaosint.com/sources/google-images-api-0-10-per-1-000-fast-image-api/) for related tools and use cases.
For support or requests for this actor, please start a ticket [directly on our support page](https://apify.com/johnvc/google-images-api/issues/open?fpr=9n7kx3).

Last Updated: 2026.09.09

# Actor input Schema

## `queries` (type: `array`):

Provide one or more image search queries, for example 'golden retriever puppy' or 'eiffel tower at night'. Each query is searched independently and billed per image returned.

## `maxResultsPerQuery` (type: `integer`):

Set how many images to return per query. Default 100. Values below 50 are raised to 50, the smallest page the upstream API bills as a single unit, so you receive 50 images rather than paying the same for fewer. The Actor pulls just enough pages to reach this count, then stops early when a query runs out of images.

## `gl` (type: `string`):

Set the two-letter country code for result localization, for example 'us', 'gb', 'de'. Defaults to 'us'.

## `hl` (type: `string`):

Set the two-letter interface language code for results, for example 'en', 'es', 'de'. Defaults to 'en'.

## Actor input object example

```json
{
  "queries": [
    "golden retriever puppy"
  ],
  "maxResultsPerQuery": 100,
  "gl": "us",
  "hl": "en"
}
```

# Actor output Schema

## `images` (type: `string`):

All image records stored in the default dataset, one item per unique image.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "queries": [
        "golden retriever puppy"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("johnvc/google-images-api").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "queries": ["golden retriever puppy"] }

# Run the Actor and wait for it to finish
run = client.actor("johnvc/google-images-api").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "queries": [
    "golden retriever puppy"
  ]
}' |
apify call johnvc/google-images-api --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,johnvc/google-images-api"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/bvAQMqCbp6wE53JzK/builds/fh3ZKm4pFYn6dXgDa/openapi.json