The Cat MCP for AI. Search, filter, and manage cat images instantly.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
The Cat MCP Server gives your AI client direct access to a vast database of cat images and breed information.
Use it to search for specific breeds, filter millions of photos by attributes like size or coat type, and manage personal collections of favorite images and votes, all through natural conversation with your agent.
What AI agents can do with The Cat Automation
Create favourite
Saves a specific image ID to your personal list of saved favorites.
Create vote
Registers an up or down vote for an image, tracking your account's interaction history.
Get favourites
Retrieves a list of all the images you have previously marked as favorites.
Find cat photos using filters for size, type, and specific breed names with search_images.
List all known breeds or search for a specific one to get detailed characteristics via list_breeds or search_breeds.
Save images you like using create_favourite and record your support with create_vote.
Check saved favorites or view all votes cast by retrieving data with get_favourites or get_votes.
Send your own cat image to the API using base64 encoding via upload_image for processing.
Ask an AI about this
Waiting for input…
What AI agents can do with The Cat MCP Server: 9 Tools for Media Retrieval
These tools let you search cat images, identify breeds, or manage media collections right from your chat interface.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using The Cat on VinkiusCreate Favourite
Saves a specific image ID to your personal list of saved favorites.
Create Vote
Registers an up or down vote for an image, tracking your account's interaction...
Get Favourites
Retrieves a list of all the images you have previously marked as favorites.
Get Image
Gets detailed information about a single cat image using its unique ID.
Get Votes
Pulls records showing all the votes you have cast on images through your account.
List Breeds
Returns a full, categorized list of every known cat breed available in the database.
Search Breeds
Narrows down the available breeds by matching a specific name or keyword.
Search Images
Finds cat images using multiple filters, including size, type, and breed criteria.
Upload Image
Processes a new image you provide by sending it to the API for storage and metadata...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The The Cat integration is available immediately — no restart needed.
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 The Cat, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ 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
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by The Cat API. 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
Built on the Model Context Protocol (MCP) for 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 connection provides 9 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Sourcing specific images used to mean endless clicking through generic search results., Solved with Vinkius AI Gateway
Today, if you need a photo of a 'medium-sized British Shorthair,' you're stuck in a web browser. You click the breed filter, then the size slider, and hope the site's internal tags match what you want. If they don't, you're left with hundreds of irrelevant results that still require manual filtering.
With The Cat MCP Server, your agent handles it all. You ask for the image parameters—breed, size, type—and the tool runs `search_images`. It doesn't just give you a bunch of pictures; it gives you clean data points and the exact links to what you asked for.
The Cat MCP Server: Manage your collections with dedicated tools.
Manual management requires opening multiple tabs. You find a cat photo, remember it, open another tab later, and try to copy the URL or save the ID somewhere else so you don't forget it. It’s messy and easily lost.
The server fixes that by giving you dedicated tools like `create_favourite`. Now, when your agent finds a cat photo you love, you just tell it to 'Save this,' and the tool handles the clean recording of the ID into your personal collection.
What your AI can actually do with this
The Cat MCP Server hooks your AI client directly into a massive database of cat pictures and breed profiles. You don't have to sift through millions of photos yourself; your agent handles the heavy lifting. It’s built for people who need specific cat data—whether you’re trying to figure out if an unknown kitty is a Maine Coon or just some fluffy stray, or you just wanna build up a killer collection of pics.
This thing lets your agent act on image metadata and breed info right inside your chat.
When you use the search_images tool, you can narrow down cat photos using multiple filters. You don't just type 'cute'; you specify things like size (is it small or massive?), coat type, or even a specific breed name to find exactly what you’re looking for.
If you need to know more about the types of cats out there, you can use list_breeds to pull up a full, categorized list of every known cat breed in the database. If you already have an idea of what you want, search_breeds lets you quickly filter that huge roster down by matching a name or keyword.
Beyond just searching, your agent can get deep into specific details. You can run get_image using a cat's unique ID to pull up all the detailed information associated with that single photo—it’s not just a picture; it's a data sheet. If you need more context on what a breed actually is, you can use get_image alongside getting details about the specific image.
Managing your personal taste is simple. When you spot a cat you dig, you run create_favourite, and it saves that specific image ID to your private list of favorites. Later, if you want to see everything you've bookmarked, you just call get_favourites to retrieve the full list.
Want to show some support? You can record your vote using create_vote, letting your account track whether you liked or disliked an image. To check out your voting history—what cats you've supported or downvoted—you run get_votes. It pulls up every single vote your account has cast.
If you find a cat picture that isn't in the database yet, no sweat. You can feed it to the system using upload_image. This tool processes the new photo you send via base64 encoding and generates all the necessary metadata for storage. It gets your own content into the mix.
Your agent coordinates these actions automatically. For instance, you tell it: 'Find me small Siamese cats I haven't seen before.' It uses search_images with size filters and breed criteria. Then, when it finds a winner, you can hit create_favourite. If the cat is particularly photogenic, you might use get_image to read about its pedigree before calling create_vote.
The whole thing flows naturally through your chat interface.
019e5d5e-4042-70fd-8328-ed00e53cd83b 
Here's how it actually works
The bottom line is that you talk to your AI, it talks to The Cat API via this server, and you get clean, actionable JSON back.
Subscribe to The Cat MCP Server and provide your unique API key.
Your AI client sends a request (e.g., 'Show me Maine Coon images').
The server executes the appropriate tool (search_images) and returns structured data about cat breeds or photos directly to your agent.
Who is this actually for?
This is for developers who need reliable access to structured media metadata. Think content creators building web features or data scientists running image-based classification tasks. It’s perfect for anyone whose job requires searching, filtering, and managing vast catalogs of visual assets.
Needs to quickly source highly specific images (e.g., 'a Scottish Fold kitten') for a media project without manually browsing stock photo sites.
Builds frontend features that allow users to search, filter, and save media content directly using the create_favourite tool.
Needs a repeatable way to pull structured metadata about cat breeds or image properties into a database for analysis.
What Changes When You Connect
Filtering is precise. Instead of getting a generic dump of photos, you tell the agent to use search_images with filters for size or type. You get targeted results, not noise.
You build stateful interactions. The ability to run create_favourite and create_vote means your AI client can manage user behavior directly against the API's backend.
Breed research is simple. Use list_breeds once to see all options, then use search_breeds when you need to pinpoint one specific type of cat for a project.
Media input is supported. Don't just read data—upload it. The upload_image tool lets your agent ingest and process new media directly into the system.
Tracking personal history works right out of the box. You can check what you saved with get_favourites, or review your voting activity using get_votes.
See it in action
Curating a media gallery for a client site.
The developer needs images of only Siamese cats that are also classified as small. Instead of writing complex API calls, they prompt their agent: 'Find me small Siamese cat photos.' The agent executes search_images, applying both the breed and size filters, and returns a clean list for immediate use.
Building a community voting feature.
A site wants users to vote on the best-looking cat of the day. The agent handles this by running create_vote when a user clicks 'upvote' or 'downvote,' logging the interaction without needing complex backend logic.
Researching pet genetics for educational content.
A writer needs to confirm the exact details of the Maine Coon. They use the agent to execute search_breeds('Maine Coon') and immediately get back detailed characteristics, which they can then quote directly into their article.
Adding user-submitted content.
A community manager gets a high-resolution cat picture from a user. They don't have to manually resize it; they just pass the base64 data to the agent, which runs upload_image and handles the storage process.
The honest tradeoffs
Searching everything at once.
Asking the AI: 'Give me all images and tell me about breeds.' This is too vague, and the agent won't know whether to run search_images or list_breeds, resulting in an error or incomplete data set.
Always narrow your request. If you need breed details first, start with 'What are the cat breeds?' (which runs list_breeds). If you want photos, use 'Search for Bengal cats' (which runs search_images). Use dedicated tools.
Treating it like a general text API.
Asking: 'Tell me what kind of cat is in this picture.' The agent can't just 'see' the image. It needs you to pass the photo data first, or use search tools with descriptive keywords.
If you have an image, first try running upload_image. If you are searching by description, always specify your criteria for search_images (e.g., 'small', 'Maine Coon').
Relying on manual browser actions.
Copying breed names from a website and manually checking them against an API doc. This is slow, error-prone, and requires context switching.
Use the server to get structured data directly. Run search_breeds('breed name') through your agent. The tool returns clean JSON every time, skipping all manual copy/paste steps.
When It Fits, When It Doesn't
You should use this MCP Server if your workflow requires filtering or managing large catalogs of visual media assets based on structured criteria (breed, size, type). It's ideal for building content engines, image galleries, or community features that rely on user interaction tracking.
However, don't use it if your goal is simple text generation or general knowledge lookup. If you just need to know 'What are the top 5 most popular cat breeds?' and don't care about images, a basic search engine might suffice. And never use this server if you only need raw, unclassified image files—you must use upload_image first for metadata processing.
The core strength is using tools like search_images and pairing it with list_breeds, making the whole process highly structured.
Questions you might have
How do I find out all available cat breeds using The Cat MCP Server? +
You run list_breeds. This tool immediately pulls a complete, structured list of every known breed into your agent's context, letting you see what's possible before you start searching.
What is the difference between using `search_breeds` and `search_images`? +
list_breeds gives you all names. Use search_breeds when you know a name but need to verify it. Use search_images when you want actual photos, allowing you to filter by size and type as well.
Can I upload my own cat photo using the `upload_image` tool? +
Yes, that's what it does. You pass your base64 encoded image data to upload_image, and the API stores it while generating metadata for you.
If I use `get_favourites`, do I get a simple list of links? +
No, it retrieves structured data. You'll get details about your favorite images, including IDs and associated information, making them ready for further processing by your agent.
Do I need to run `get_votes` before using the voting tools? +
No, they are separate. You use create_vote when you want to cast a vote. You only run get_votes later if you actually need to review your own historical activity.
When using `search_images`, how do I apply specific filters like size or breed? +
You pass parameters directly into the search request. For example, you can narrow results by specifying a minimum image size (e.g., 'large') or filtering by a particular cat breed name.
What do I need to know before running `get_image`? +
The tool requires the unique ID of the specific cat picture you want details for. You must have this image ID—it cannot guess it or pull it from a general search result.
If I use `get_favourites`, how do I get full metadata for those saved images? +
The get_favourites tool provides basic records. To retrieve the complete, detailed data set—like high-resolution links or specific attributes—you must feed one of the returned IDs into the get_image tool.
How do I find high-quality cat images of a specific breed? +
You can use the search_images tool and specify the size as 'full' and has_breeds as true. To find a specific breed's ID first, use the search_breeds tool.
Can I see all the images I have previously favorited? +
Yes! Use the get_favourites tool. It will retrieve a list of all cat images you have saved to your account.
How do I cast a vote on a cat image? +
Use the create_vote tool. You'll need the image_id and a value (1 for an upvote, 0 for a downvote).
We've already built the connector for The Cat. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 9 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.