Get started

Supportivekoala for AI agents

Supportive Koala automates image generation from customizable templates, letting teams create branded visual content, such as social graphics, through an API. 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.

Connect SupportivekoalaSee the 6 actions ↓
Design and imagesAPI keyMCP + RESTsupportivekoala.com
AUDIT LOG · SUPPORTIVEKOALAPOLICY: acme-support
09:41:07 · claude · u_8f2read
supportivekoala.list_images
List Images✓ allowed · 212ms
09:41:08 · claude · u_8f2read
supportivekoala.list_templates
List Templates✓ allowed · 164ms
09:41:09 · claude · u_8f2write
supportivekoala.create_image
Create Image✓ approved · approved by user
EVERY SUPPORTIVEKOALA CALL, ON THE RECORD
01 · USE CASES

What agents do in Supportivekoala.

01

Create an image from a template

Generate a new branded image from an existing template, filling in text for a specific social post.

02

List templates before generating

Pull the list of available templates so a user can pick the right one before generating an image.

03

Look up a template by ID

Retrieve a specific template's details as a read-only check before reusing it for a new image.

02 · ACTIONS

6 Supportivekoala actions, graded by risk.

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

read

3

Look things up. Allowed by default.

  • supportivekoala.list_images
    List Images
  • supportivekoala.list_templates
    List Templates
  • supportivekoala.retrieve_template
    Retrieve Template by ID

write

3

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

  • supportivekoala.create_image
    Create Image
  • supportivekoala.create_template
    Create Template
  • supportivekoala.register_user
    Register User

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Supportivekoala in three steps.

  1. 01Your users connect SupportivekoalaThey add their Supportivekoala api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Image” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Supportivekoala 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('supportivekoala', {
  read: 'allow',
  write: 'ask',        // create_image
  destructive: 'deny',  
})

# 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 Supportivekoala connects.

Users add their Supportivekoala 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 Supportivekoala 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 Supportivekoala from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More design and images apps.

Figma53 actionsAbyssale4 actionsAdrapid3 actionsCloudinary109 actionsPenpot90 actionsImgix53 actionsCanva49 actionsBannerbear33 actions
ALL DESIGN AND IMAGES APPS →
07 · FAQ

Supportivekoala and Arc0, answered.

Q01

Can I use Supportivekoala with Claude, ChatGPT or Cursor?

Yes. Connect Supportivekoala 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 Supportivekoala actions you allow.

Q02

How do users connect Supportivekoala?

Users add their Supportivekoala 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 Supportivekoala actions can my agent take?

6 in total: 3 read, 3 write and 0 destructive, such as “create Image”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Supportivekoala?

Yes. Allow read actions and deny writes in the Supportivekoala policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Supportivekoala too?

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

Get started

Plug Supportivekoala into your agent.

Your users connect Supportivekoala once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.

Connect SupportivekoalaBrowse all apps →

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