# Getty Images MCP Server (slim)

> The Getty Images MCP Server is a remote MCP server from Getty Images that lets AI assistants and agents search, read metadata for and download the creative, editorial and archival images and video in a customer's Getty Images agreement.

- Full: https://www.anchorterminal.com/tools/getty-images-mcp.md (~8,100 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/getty-images-mcp.json · canonical https://www.anchorterminal.com/tools/getty-images-mcp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-27 · pricing https://www.anchorterminal.com/tools/getty-images-mcp#pricing · reviews https://www.anchorterminal.com/tools/getty-images-mcp#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**F · 32.4/100 · rank #1136 of 1217 · #13 in Data providers · not agent-ready · confidence low**


Assessment: The server reaches Getty Images' licensed creative and editorial catalogue through OAuth client credentials, with a published limit of 20 queries a second. Access needs a Getty agreement and credentials from an account representative, the Web Service Terms aren't public, the tools can't be read without a key, and the content licence bars AI use unless the agreement allows it.

## Facts

- Kind: MCP server · vendor: Getty Images · category: Data providers · legal entity: Getty Images Holdings, Inc. · provenance 100/100 · data quality 56/100
- Endpoint: `https://mcp.gettyimages.com/v1` ()
- Auth: OAuth · pricing: Paid · x402: no · licence: Proprietary hosted service, available under a Getty Images agreement and Getty's Web Service Terms, which aren't published. Content is licensed under the Getty Images content licence agreement (last updated April 2026) unless the customer's agreement says otherwise
- Probe metrics: not measured yet (probes haven't run)
- MCP endpoint: `https://mcp.gettyimages.com/v1`, behind Amazon API Gateway and CloudFront. Unauthenticated `initialize` and `tools/list` answer 401. Transport not stated in the docs
- OAuth: Issuer `https://authentication.gettyimages.com`. Grants authorisation code (PKCE S256), client credentials and refresh token. Client authentication by secret only. No scopes, dynamic client registration or revocation endpoint listed
- Tools: Not published. The developer page names search for images and videos, asset metadata and download, and asks agents to discover tools at run time
- Rate limit: 20 queries a second on the MCP server. The REST API's limits are set per API key, and overruns answer 429 `Account Over Queries Per Second Limit`
- Who can use it: Customers with an active Getty agreement, such as Premium Access or an Editorial Subscription, and business partners. Key and secret from the account representative after accepting the Web Service Terms
- Content: Creative, editorial (news, sport, entertainment) and archival images and video, limited to the customer's agreement. Getty says 50,000 to 80,000 new images a week, mostly editorial, reach the API when they reach its websites
- AI use of content: Barred for machine learning or AI purposes, including metadata, unless the agreement authorises it. Creative content may be searched, indexed, sorted and edited with AI internally. No training, fine-tuning or evaluation. Rights end if an AI tool uses content for its own purposes
- REST API: The Getty Images API v3 at `https://api.gettyimages.com/v3/`, with an OpenAPI 3.0.4 file of 66 paths at `https://api.gettyimages.com/swagger/v3/swagger.json`. It is the older route to the same catalogue; how the MCP tools map to it isn't documented
- Status: Posts on developer.gettyimages.com/status/ for the API and websites, back to 2023. Last 90 days, one incident, 500 errors from about 05.45 to 08.20 Pacific time on 27 August 2026

- Scores: Reliability 50, Performance pending, Schema & documentation 19, Agent ergonomics 24, Security & auth 40, Payments & pricing 0, Task success pending, Maintenance & community 28, Transparency & trust 68 · total over the 7 assessed categories
- Why: Reliability, Graded with the hosted lines, on the remote MCP server. · Schema & documentation, No machine-readable contract for the MCP tools could be read. · Agent ergonomics, Graded on the MCP server without reading its tools. · Security & auth, OAuth 2.0 with an API key and secret per customer, tied to the agreement and issued by Getty. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read as a closed hosted service. · Transparency & trust, The editorial half.
- Sources: 24, open questions: 10, both in the full twin
- Capabilities: data.knowledge
- JSON: https://www.anchorterminal.com/api/v1/tools/getty-images-mcp.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/getty-images-mcp.svg` or a link to https://www.anchorterminal.com/tools/getty-images-mcp from a page on gettyimages.com or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Ask the person for the Getty API key and secret, which only their Getty account representative can issue after the Web Service Terms are accepted
2. Exchange the key and secret for a bearer token at authentication.gettyimages.com and reuse it until it expires, since token requests count against the rate limit
3. Read `tools/list` at the start of each session rather than hard-coding tool names, because Getty says tools and parameters will change
4. Check whether an asset is editorial before suggesting commercial use, since editorial content isn't licensed for advertising or promotion
5. Don't pass downloaded images or their metadata to a model or tool that trains on inputs; the licence bars training and ends rights if an AI tool uses content for itself

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Wikimedia REST API | B | 66.5 | data.knowledge | https://www.anchorterminal.com/tools/wikimedia.min.md |
| Diffbot | C | 54.3 | data.knowledge | https://www.anchorterminal.com/tools/diffbot.min.md |
| CoinGecko x402 API | BB | 71.7 | same category | https://www.anchorterminal.com/tools/coingecko-x402-api.min.md |
| Massive (formerly Polygon.io) | B | 69.8 | same category | https://www.anchorterminal.com/tools/massive.min.md |
| Open-Meteo | B | 63.4 | same category | https://www.anchorterminal.com/tools/open-meteo.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)