Cats for AI agents

The Cat API gives access to a large library of cat images, breed data, and facts, useful for apps that need pet content or breed lookups. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Design and imagesAPI keyMCP + RESTthecatapi.com
AUDIT LOG · CATSPOLICY: acme-support
09:41:07 · claude · u_8f2read
cats.list_votes
List Votes✓ allowed · 212ms
09:41:08 · claude · u_8f2read
cats.get_vote
Get Vote by ID✓ allowed · 164ms
09:41:09 · claude · u_8f2write
cats.create_vote
Create Vote✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
cats.delete_vote
Delete Vote✕ blocked · policy: deny
EVERY CATS CALL, ON THE RECORD
01 · USE CASES

What agents do in Cats.

01

Search cat images by breed

Search for cat images filtered by a specific breed to use in an app or design.

02

Look up breed details

Look up a cat breed's facts and traits before writing content about it.

03

Confirm before deleting an image

Confirm before deleting an uploaded image, since it's removed from the library permanently.

02 · ACTIONS

18 Cats actions, graded by risk.

Every Cats action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

13

Look things up. Allowed by default.

  • cats.get_vote
    Get Vote by ID
  • cats.get_breed
    Get Cat Breed by ID
  • cats.get_image
    Get Cat Image by ID
  • cats.list_votes
    List Votes
  • cats.get_portals
    Get Cat Breeds
  • cats.get_favourite
    Get Favourite by ID
  • cats.search_breeds
    Search Cat Breeds
  • cats.search_images
    Search Cat Images
  • cats.list_categories
    List Image Categories
  • cats.list_favourites
    List Favourites
  • cats.get_image_breeds
    Get Image Breeds
  • cats.get_image_analysis
    Get Image Analysis
  • cats.list_uploaded_images
    List Uploaded Images

write

2

Create and change things. Allow, or ask the user first.

  • cats.create_vote
    Create Vote
  • cats.create_favourite
    Create Favourite

destructive

3

Delete, cancel or archive. Ask first, or deny outright.

  • cats.delete_vote
    Delete Vote
  • cats.delete_image
    Delete Image
  • cats.delete_favourite
    Delete Favourite
03 · HOW IT WORKS

Cats in three steps.

  1. 01Your users connect CatsThey add their Cats api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Vote” can wait for the user, and “delete Vote” can be denied outright.
  3. 03Any agent can actYour agent calls Cats through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('cats', {
  read: 'allow',
  write: 'ask',        // create_vote
  destructive: 'deny',  // delete_vote
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Cats connects.

Users add their Cats api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Cats connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Cats from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Cats and Arc0, answered.

Q01

Can I use Cats with Claude, ChatGPT or Cursor?

Yes. Connect Cats to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Cats actions you allow.

Q02

How do users connect Cats?

Users add their Cats api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Cats actions can my agent take?

18 in total: 13 read, 2 write and 3 destructive, such as “create Vote”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Cats?

Yes. Actions like “delete Vote” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Cats too?

Yes. The same Cats connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Cats into your agent.

Your users connect Cats once, under your brand. Your agent gets 18 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan