OKZest for AI agents

OKZest is a design automation platform that renders personalized images from reusable design templates through an API. Marketing teams use it to generate on-brand visuals at scale. 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 + RESTokzest.com
AUDIT LOG · OKZESTPOLICY: acme-support
09:41:07 · claude · u_8f2read
okzest.list_designs
List Designs✓ allowed · 212ms
09:41:08 · claude · u_8f2read
okzest.get_design
Get Design✓ allowed · 164ms
09:41:09 · claude · u_8f2write
okzest.render_image
Render Image✓ approved · approved by user
EVERY OKZEST CALL, ON THE RECORD
01 · USE CASES

What agents do in OKZest.

01

Render a personalized image

Generate an image from a saved design template with a customer's name or details filled in.

02

Check a design's editable fields

List a design's fields read-only to see what data it needs before rendering.

03

Browse available designs

List all designs in the workspace to pick the right template for a campaign.

02 · ACTIONS

4 OKZest actions, graded by risk.

Every OKZest 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.

  • okzest.get_design
    Get Design
  • okzest.list_designs
    List Designs
  • okzest.get_design_fields
    Get Design Fields

write

1

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

  • okzest.render_image
    Render Image

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

OKZest in three steps.

  1. 01Your users connect OKZestThey add their OKZest api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “render Image” can wait for the user to approve.
  3. 03Any agent can actYour agent calls OKZest 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('okzest', {
  read: 'allow',
  write: 'ask',        // render_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 OKZest connects.

Users add their OKZest 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 OKZest 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 OKZest from any agent.

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

OKZest and Arc0, answered.

Q01

Can I use OKZest with Claude, ChatGPT or Cursor?

Yes. Connect OKZest 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 OKZest actions you allow.

Q02

How do users connect OKZest?

Users add their OKZest 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 OKZest actions can my agent take?

4 in total: 3 read, 1 write and 0 destructive, such as “render Image”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in OKZest?

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

Q05

Can my own backend call OKZest too?

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

Get started

Plug OKZest into your agent.

Your users connect OKZest once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.

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