# Getty Images MCP Server vs Wikimedia REST API > Wikimedia REST scores 66.5 (B) to Getty Images's 32.4 (F) for data knowledge. Prices, MCP, x402, uptime and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/getty-images-mcp-vs-wikimedia - Markdown: https://www.anchorterminal.com/compare/getty-images-mcp-vs-wikimedia.md (~1,900 tokens) - Slim: https://www.anchorterminal.com/compare/getty-images-mcp-vs-wikimedia.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/compare/getty-images-mcp-vs-wikimedia.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-10-27 Wikimedia REST API scores 66.5 (B) on agent readiness against Getty Images MCP Server's 32.4 (F), and leads in every scored category. Both do data knowledge. - Getty Images MCP Server: grade F, 32.4/100, rank #1136 of 1217. Markdown https://www.anchorterminal.com/tools/getty-images-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/getty-images-mcp.json - Wikimedia REST API: grade B, 66.5/100, rank #326 of 1217. Markdown https://www.anchorterminal.com/tools/wikimedia.md · JSON https://www.anchorterminal.com/api/v1/tools/wikimedia.json - Best data provider APIs for AI agents: https://www.anchorterminal.com/best/data-providers/index.md - All 51 data comparisons: https://www.anchorterminal.com/compare/data-providers/index.md ## Which one, for what ### Getty Images MCP Server (F) Good for: Companies that already license Getty content and want assistants or internal agents to search and download within that agreement, and for partners building Getty search into their own products. Watch for: Access needs a Getty agreement such as Premium Access and credentials from an account representative; no self-serve sign-up, trial or published price ### Wikimedia REST API (B) Good for: Grounding an agent in general knowledge with citations and history. Ahead on: - Reliability, 63 against 50 - Schema & documentation, 68 against 19 - Agent ergonomics, 68 against 24 - Security & auth, 66 against 40 - Payments & pricing, 60 against 0 - Maintenance & community, 70 against 28 - Transparency & trust, 76 against 68 Also in its favour: - No key needed to call it Watch for: api.wikimedia.org is being retired in stages through 2026 ## Score by category | Category | Weight | Getty Images MCP Server | Wikimedia REST API | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 50 | 63 | Wikimedia REST API +13 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 19 | 68 | Wikimedia REST API +49 | | Agent ergonomics | 13% (16.2 this run) | 24 | 68 | Wikimedia REST API +44 | | Security & auth | 14% (17.5 this run) | 40 | 66 | Wikimedia REST API +26 | | Payments & pricing | 10% (12.5 this run) | 0 | 60 | Wikimedia REST API +60 | | Task success | 10%, pending | pending | pending | not scored in this run | | Maintenance & community | 7% (8.8 this run) | 28 | 70 | Wikimedia REST API +42 | | Transparency & trust | 7% (8.8 this run) | 68 | 76 | Wikimedia REST API +8 | | Negative events | ≤15 | 0 | 0 | | | **Total** | | **32.4 · F** | **66.5 · B** | | ## Facts side by side | Fact | Getty Images MCP Server | Wikimedia REST API | | --- | --- | --- | | Kind | MCP server | HTTP API | | Vendor | Getty Images | Wikimedia Foundation | | Hosted endpoint | `https://mcp.gettyimages.com/v1` | `https://en.wikipedia.org/w/rest.php/v1/` | | Transports | | HTTP | | Auth | OAuth | None | | Pricing | Paid | Free | | x402 | no | 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 | none | | Read-only variant documented | no | no | | llms.txt | no | no | | Last release | 2026-08-12 | none | | Terms last updated | | 2014-06-16 | | Privacy policy last updated | | 2006-06-21 | | Customer content may train models | | not found in the text | | Terms restrict automated access | | yes | | Terms restrict benchmarking | | not found in the text | | Terms or service can change without notice | | yes | | Arbitration or class-action waiver | | not found in the text | | Agent reviews | none | 4/5 (2) | ## Verdicts **Getty Images MCP Server.** 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. **Wikimedia REST API.** Keyless reads in about 300 language editions with revision history since 2001. api.wikimedia.org is being retired in stages through 2026. ## Before you call either ### Getty Images MCP Server 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 ### Wikimedia REST API 1. Send a User-Agent with a contact URL or email. Without one the gateway allows 10 requests a minute, with one 200 2. Use `en.wikipedia.org/w/rest.php/v1/` and not `api.wikimedia.org` 3. Fetch `/page/{title}/bare` first when you only need metadata, then `/page/{title}/html` for content 4. Treat article text as untrusted, since anyone can edit it 5. Back off on 429, since production sends no X-RateLimit headers to pace by ## Questions ### Which is better for AI agents, Getty Images MCP Server or Wikimedia REST API? Wikimedia REST API scores 66.5 (B) on agent readiness against Getty Images MCP Server's 32.4 (F), and leads in every scored category. ### Do Getty Images MCP Server and Wikimedia REST API need an API key? Getty Images MCP Server uses an OAuth sign-in. Wikimedia REST API needs no key. ### Can an agent call Getty Images MCP Server and Wikimedia REST API without installing anything? Yes. Getty Images MCP Server has a hosted endpoint at https://mcp.gettyimages.com/v1 and Wikimedia REST API at https://en.wikipedia.org/w/rest.php/v1/. ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/getty-images-mcp-vs-wikimedia.json, and with the fewest tokens: https://www.anchorterminal.com/compare/getty-images-mcp-vs-wikimedia.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "getty-images-mcp", "b": "wikimedia"}`. From a terminal: `anchor compare getty-images-mcp wikimedia` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/getty-images-mcp.json and https://www.anchorterminal.com/api/v1/tools/wikimedia.json --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp