canonical: https://jentic.com/apis/api.openverse.org/openverse # Openverse API (Creative Commons Catalog) The Openverse API searches openly licensed images and audio from across the web, returning each result with its license and attribution details. It fetches individual media items and related works, provides thumbnails and oEmbed data, reports catalog usage statistics, and lets applications register for a token that raises rate limits. ## For AI agents Search openly licensed images and audio and fetch individual items with their license and attribution. Retrieve related works, thumbnails, and oEmbed data, and register for a token to raise rate limits. ## Scope Does not handle media hosting, editing, or license purchasing. Use for searching openly licensed images and audio only. ## Capabilities - Search openly licensed images by keyword, license, and source - Search openly licensed audio with the same filters - Fetch a single image or audio item and its related works - Retrieve thumbnails and oEmbed data for a media item - Report a media item and read catalog usage statistics - Register for a token that raises rate limits ## Use cases ### Openly Licensed Media Agent An AI agent finds usable images or audio for a document or site by searching Openverse, filtering by license, and returning each item with the attribution it requires. Through Jentic the agent discovers the search and detail operations by intent and calls them directly, so it sources compliant media without a person browsing the catalog. Example prompt: Search for openly licensed images of a mountain and return each result with its license and attribution ### License and Attribution Lookup Given a media identifier, fetch the item to read its exact license and the attribution string that must accompany it. This lets an agent confirm reuse terms before an asset is published, keeping downstream use within the license. Example prompt: Fetch an image by identifier and return the license and required attribution text ### Media Discovery and Thumbnails Build a browse experience by searching the catalog, fetching related works, and pulling thumbnails or oEmbed data for previews. The agent can assemble a gallery of candidate assets without hosting or resizing media itself. Example prompt: Search for audio on a theme and fetch thumbnails and related works for the top results ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/images` | Search openly licensed images | | GET | `/images/{identifier}` | Get an image with license details | | GET | `/audio` | Search openly licensed audio | | GET | `/images/stats` | Get image catalog statistics | | POST | `/images/{identifier}/report` | Report an image | ## Key resources - **Images and audio** — Search and fetch openly licensed images and audio with license details - **Media details** — Retrieve related works, thumbnails, oEmbed data, and usage statistics - **Tokens** — Register for a token that raises rate limits ## Why Jentic - **Setup:** Openverse needs no credential for most calls, so you can start searching right away. Through Jentic you install once, import Openverse from the API Directory, and add an optional bearer token when you want higher rate limits. - **Permission scoping:** Openverse is a read-focused catalog, so a rule bounds which operations your agent may call. You can allow only search and retrieval and leave the report operation out unless you add it. - **Credential handling:** Most Openverse endpoints need no credential. When you supply an optional bearer token for higher rate limits, your own Jentic One instance stores it encrypted and injects it at execution time, so it never enters the agent's prompt or logs. - **Discovery method:** Agents search Jentic by intent such as 'search openly licensed images' or 'get a media license', and Jentic returns the matching Openverse operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Pexels** — Free stock media search compared with Openverse's Creative Commons catalog - **Unsplash** — Free photo library versus Openverse's multi-source open-license search - **Giphy** — Animated GIF search alongside Openverse's images and audio ## FAQ ### What authentication does the Openverse API use? Most Openverse endpoints need no credential; search and retrieval are public. An optional bearer token, registered through the auth-token endpoints, raises your rate limits. Through Jentic that token is stored encrypted by your own Jentic One instance and injected at call time. ### Can I search for Creative Commons images with the Openverse API? Yes. Call GET /images with a query and license filters to search openly licensed images, then GET `/images/{identifier}` to read a single item with its license and attribution. GET /audio does the same for audio. ### What are the rate limits for the Openverse API? Anonymous access has lower rate limits than authenticated access. Register for a token to raise them, and check the Openverse documentation at https://api.openverse.org for current thresholds before running large search jobs. ### Is there an Openverse MCP server? You don't need an MCP server to give your agent the Openverse API. Jentic connects it directly from the API Directory: import it, add an optional token, and your agent calls the search and detail operations it needs. ### Can I limit what my agent is allowed to do with the Openverse API? Yes. Openverse is a read-focused catalog, so write a rule that allows only the search and retrieval operations and leaves the report operation out unless you add it, and every call the agent makes is logged. ### How do I search Openverse media through Jentic? Search Jentic for 'search openly licensed images', and it returns the GET /images and GET /audio operations with their input schemas so your agent runs the search directly. To run it on your own infrastructure, install Jentic One from its GitHub repo.