Shutterstock MCP. Search assets and audit licenses with AI.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Shutterstock MCP lets your AI agent search a massive library of media assets—images, videos, audio, and editorial content. Your agent can pull metadata, check licensing rules, and audit entire collections directly from natural language prompts.
It's like having an autonomous art buyer connected to the world's largest stock media vault.
What your AI agents can do
Get audio details
Retrieves technical data (like BPM) for a specific audio track ID.
Get image details
Gets metadata and specs for one particular image asset ID.
Get license history
Pulls a list of all assets you’ve previously licensed or used, along with dates and details.
Your agent searches for images, videos, audio tracks, and editorial photos within the Shutterstock vault using specific criteria.
You get detailed technical specs (like resolution or BPM) by running dedicated tools against a known asset ID.
The server tracks your licensing history and lists the contents of your personal, saved media collections.
Ask AI about this MCP
Supported MCP Clients
Waiting for input…
Shutterstock MCP Server: 9 Tools for Media Search
These nine tools allow your agent to interact with every major part of the Shutterstock library—from deep searches to license history checks.
019d7607get audio details
Retrieves technical data (like BPM) for a specific audio track ID.
019d7607get image details
Gets metadata and specs for one particular image asset ID.
019d7607get license history
Pulls a list of all assets you’ve previously licensed or used, along with dates and details.
019d7607get video details
Retrieves technical specifications (like frame rate) for one video asset ID.
019d7607list collections
Shows a list of all saved or organized image collections you have within your account.
019d7607search audio
Searches the library for background music and sound effects based on keywords or genre.
019d7607search editorial
Searches only for editorial photos, which are typically news-based and not designed for commercial use.
019d7607search images
Returns metadata and preview URLs when searching the main image library using keywords.
019d7607search videos
Searches stock video footage, letting you filter by quality, frame rate, and duration.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Shutterstock, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
This MCP server gives your AI client deep access to Shutterstock's massive media library. You don't have to spend hours clicking through tabs or running separate searches; you just tell your agent what you need, and it handles the heavy lifting across images, videos, audio, and editorial content. It acts like an autonomous art buyer who knows exactly which asset fits the job.
Search Media Libraries: Your agent can dig into specific media types using dedicated search tools. You'll use search_images to pull metadata and preview links from the main image catalog just by giving it keywords. If you need stock video footage, run search_videos, and your agent lets you filter results based on quality requirements, frame rate needs, and how long the clip is.
For background music or sound effects, use search_audio to search by genre or specific keywords. You can also limit searches solely to news-based photos—those are editorial assets—by triggering search_editorial.
Retrieve Asset Metadata: Once your agent finds an asset ID you like, it pulls the technical specs immediately. If you're looking at a picture, running get_image_details provides all the metadata and specs for that specific image. For video clips, get_video_details retrieves crucial technical information, like the frame rate. When you nail down an audio track ID, your agent uses get_audio_details to pull detailed technical data, such as the Beats Per Minute (BPM).
Audit Usage Rights and Collections: This server manages more than just searching; it helps you keep tabs on what you've already used. To see everything you’ve licensed or used before, triggering get_license_history pulls a full list of assets, including the dates and details of your previous usage. You can also check out your personal storage by running list_collections, which shows every saved or organized image collection you've built in your account.
If your agent spots an asset that fits, it checks its technical specs immediately: for example, if you find a perfect video clip, the server tells you exactly what frame rate it has. If you need music, search_audio finds the right tracks and then get_audio_details confirms the BPM so your project syncs up perfectly.
You can run searches across multiple asset types—you're not stuck in one corner of the site. The agent lets you find a suitable image using search_images, check its specs with get_image_details, and then compare it to an editorial photo found via search_editorial to make sure you’ve got the right rights for your commercial needs.
Need to confirm what's in your private stash? Use list_collections to see all those organized image folders. Want proof of purchase or usage? get_license_history gives you a bulletproof list of everything you've already pulled and paid for. These tools work together, letting your agent manage the whole process—from initial search query using search_videos, through detailed analysis with get_video_details, right down to keeping a clean record with get_license_history.
You never have to manually switch contexts; you just prompt it once and let the system run the necessary sequence of checks.
How Shutterstock MCP Works
- 1 You prompt your AI client with a request (e.g., 'Find me four high-res images of dogs playing outdoors').
- 2 The agent identifies the correct tool (
search_images) and passes the necessary parameters to the Shutterstock MCP. - 3 The server runs the search, pulls back metadata, and delivers the results directly to your client for review.
The bottom line is: you talk to your AI client like you're talking to a librarian who has instant, deep access to every corner of Shutterstock’s catalog.
Who Is Shutterstock MCP For?
Anyone whose job involves finding specific, high-quality media assets quickly. This is for the Marketing Manager who needs 15 hero images by noon, the Video Editor building a commercial spot and needing perfect background music, or the Licensing Specialist doing a full audit of corporate asset usage.
Runs bulk searches across search_images and search_videos, filtering dozens of options until they find the perfect look for a campaign.
Uses search_editorial to pull non-commercial, news-related assets that fit a brand's narrative or blog post.
Coordinates asset pulls by running get_video_details to confirm the required 4K resolution before incorporating stock footage into an edit.
What Changes When You Connect
- Stop guessing which tool to use. Your agent handles the routing, letting you search images (
search_images), videos (search_videos), or audio tracks (search_audio) all through one conversation. - Verify asset quality instantly. Instead of clicking into a video to check specs, run
get_video_detailsand get hard data like frame rate straight back. - Never worry about rights again. Use
get_license_historyto see exactly what you’ve paid for, or uselist_collectionsto organize assets before a big project starts. - Filter down massive results fast. You can specify if you need commercial images (
search_images) or news-related editorial content usingsearch_editorial. - Deep dive into audio tracks. Need more than just the track name? Use
get_audio_detailsto pull technical specs like BPM and duration.
Real-World Use Cases
The Quarterly Campaign Refresh
A marketing manager needs 10 hero images for a new campaign. Instead of running ten separate Google Image searches, they ask their agent to run search_images with specific keywords and aspect ratios. The agent returns metadata on the top five options that fit the budget and style immediately.
The Podcast Episode Production
A video producer needs a background soundscape for a segment. They use search_audio to find 'tense' music, then run get_audio_details on the top result to confirm it has a loopable structure and the right BPM before locking it in.
The Legal Compliance Check
A licensing specialist needs to prove what was used last year. They run get_license_history through their agent, which instantly compiles a clean report detailing every asset ID and its associated license type for compliance review.
The Global Content Audit
A creative director needs to see all the images saved in a specific folder. They simply run list_collections via their agent, which immediately provides an overview of every asset ID and its associated metadata, saving hours of manual browsing.
The Tradeoffs
Searching only by vague keywords
Asking the AI client: 'Find some good pictures for my site.' This returns thousands of irrelevant assets and zero actionable data.
→
Be specific. Use search_images with multiple constraints: 'Search images, minimum resolution 4k, aspect ratio horizontal, subject golden retriever.' Tell your agent exactly what you need.
Ignoring content type restrictions
Using a general search when the client only needs news coverage. The result is getting commercial stock photos instead of editorial pieces.
→
Always use search_editorial when your subject matter must be journalistic or non-commercial. This tool keeps those two types of content separate.
Assuming metadata is available
Getting an asset ID and assuming it has the resolution you need, only to find out later that it's low quality.
→
Always verify. After getting a video ID, run get_video_details immediately to confirm its maximum frame rate or resolution before committing to the asset.
When It Fits, When It Doesn't
Use this MCP if your job involves managing, finding, or auditing large quantities of visual media assets (photos, videos, music). You need to know what you have and if you can use it.
Don't use this just because you want a search tool. If you only need basic web searching or simple text data retrieval, that’s for a general-purpose knowledge base connection. This is about structured media assets.
If your primary task is to find the best asset based on visual criteria, rely on search_images and search_videos. If you're dealing with rights or usage, use get_license_history. If you need technical specs (like BPM or resolution), always follow up a search with the corresponding 'get_details' tool. It’s about confirming data points, not just finding pictures.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Shutterstock. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 9 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Sifting through assets shouldn't feel like an archaeological dig.
Right now, pulling a single asset requires jumping between the main search page, then clicking into the details tab to check resolution, and finally navigating to a separate licensing section. You copy IDs, you switch tabs, you wait for multiple pages to load. It’s slow.
With this MCP server, your agent handles the whole thing in one prompt. Ask it to find videos matching X criteria *and* confirm they are 4K resolution using `get_video_details`. You get a clean answer without ever leaving your chat window.
The Shutterstock MCP Server gives you immediate license and asset status.
Previously, checking usage rights meant logging into the account history section, finding the specific ID of the asset in question, and manually verifying its license type. It was a tedious audit process.
Now, running `get_license_history` instantly compiles that data for you. You get an auditable record delivered directly to your agent—no clicking, no searching through folders, just clean, usable compliance data.
Common Questions About Shutterstock MCP
How do I search for different media types using the Shutterstock MCP Server? +
You use dedicated tools for each type. Use search_images for photos, search_videos for footage, and search_audio for music tracks.
What is the difference between `search_images` and `search_editorial`? +
search_images targets commercial stock media that you can use in ads. search_editorial, by contrast, searches news-based content meant for journalism.
If I find an asset ID, which tool should I use to check its specs? +
Use the dedicated function: get_video_details for videos, get_image_details for photos, or get_audio_details for music tracks.
Can I see all my saved assets in one place using list_collections? +
Yes. The list_collections tool shows you every structured folder of images you've grouped, giving you an overview of your saved content.
What specific metrics can I pull using `get_audio_details`? +
The tool returns detailed metadata, including BPM (beats per minute), key signatures, and duration. You get structural data points beyond just the preview link, allowing your agent to classify tracks accurately.
What should I expect if an ID fails with `get_image_details`? +
If a provided asset ID is invalid or inaccessible, the tool returns a structured error code and an empty payload. Your agent can then use this specific error response to prompt you for correction or skip the item.
Does using `get_license_history` verify my current account status? +
Yes, the tool pulls a detailed record of past usage and licensing agreements tied to your credentials. It confirms which assets were licensed, when they expired, and what specific rights you held at that time.
Are there rate limits or best practices for using `search_videos`? +
While the server handles high volume, repeated searches should be managed by implementing a delay between calls. Focus on narrowing filters (quality, duration) to keep responses efficient and within standard API call quotas.
Can the integration forcefully license or automatically purchase an image? +
No. By structural design, this module is strictly bound as an observational and search lens tailored purely around querying assets violently efficiently. It explicitly omits write protocols preventing your autonomous agent from accidentally sabotaging valid corporate wallets or unintentionally mass-licensing redundant data.
Can it search for specific internal user collections or boards? +
Yes, utilizing the explicit list_collections operational protocol, the token directly verifies and systematically grabs all active native groupings created rigidly beneath the account bounding that token natively.
Is the Editorial access separated structurally from the standard image search? +
Yes aggressively. Because editorial resources operate identically under completely distinct structural usage and strict rights matrices, we forcibly separate standard asset queries (search_images) strictly away from the rigorous editorial boundaries specifically bound uniquely under search_editorial.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
NOAA Tides & Currents API
Monitor tidal data — audit water levels and predictions via AI.
Odicci
Launch interactive marketing campaigns with gamification elements like spin wheels, quizzes, and scratch cards that capture leads.
GrabFood Partner
Automate GrabFood restaurant operations — manage orders, update menus, control store status, and run marketing campaigns directly from any AI agent.
You might also like
Daftra
Equip your AI agent to manage your ERP, accounting, and client relations directly via the Daftra API.
Beehiiv
Automate newsletter management via Beehiiv — manage publications, subscribers, analytics, and posts natively with your AI agent.
HID Origo
Automate identity and access management via HID Origo — manage mobile identities, users, and readers directly from any AI agent.