Slazzer for AI agents

Slazzer offers AI image editing APIs that remove backgrounds, upscale photos, relight scenes, and clean up product catalog images for online sellers. 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 Slazzer See the 9 actions ↓

Design and imagesAPI keyMCP + RESTslazzer.com

AUDIT LOG · SLAZZERPOLICY: acme-support

09:41:09 · claude · u_8f2write

slazzer.create_catalog_image

Create Catalog Image✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

slazzer.remove_image_background

Remove Image Background✕ blocked · policy: deny

EVERY SLAZZER CALL, ON THE RECORD

01 · USE CASES

What agents do in Slazzer.

Remove a background from a product photo

Remove the background from a product image so it drops cleanly into a catalog or ad template.

Preview an edit before replacing the original

Generate an upscaled or relit version of an image for review before it replaces the original file.

Batch-process a catalog of images

Create catalog images for a batch of product photos in one pass, keeping style consistent across the set.

02 · ACTIONS

9 Slazzer actions, graded by risk.

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

read

Look things up. Allowed by default.

No read actions.

write

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

slazzer.create_catalog_image
Create Catalog Image
slazzer.replace_sky
Replace Sky
slazzer.relight_image
Relight Image
slazzer.upscale_image
Upscale Image
slazzer.colorize_old_photo
Colorize Old Photo
slazzer.enhance_image_colors
Enhance Image Colors
slazzer.edit_automobile_image
Edit Automobile Image
slazzer.generate_image_shadow
Generate Image Shadow

destructive

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

slazzer.remove_image_background
Remove Image Background

03 · HOW IT WORKS

Slazzer in three steps.

01Your users connect SlazzerThey add their Slazzer api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Catalog Image” can wait for the user, and “remove Image Background” can be denied outright.
03Any agent can actYour agent calls Slazzer 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('slazzer', {
  read: 'allow',
  write: 'ask',        // create_catalog_image
  destructive: 'deny',  // remove_image_background
})

# 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 Slazzer connects.

Users add their Slazzer 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 Slazzer 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 Slazzer 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 actions

Abyssale4 actions

Adrapid3 actions

Cloudinary109 actions

ALL DESIGN AND IMAGES APPS →

07 · FAQ

Slazzer and Arc0, answered.

Q01

Can I use Slazzer with Claude, ChatGPT or Cursor?

Yes. Connect Slazzer 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 Slazzer actions you allow.

Q02

How do users connect Slazzer?

Users add their Slazzer 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 Slazzer actions can my agent take?

9 in total: 0 read, 8 write and 1 destructive, such as “create Catalog Image”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Slazzer?

Yes. Actions like “remove Image Background” 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 Slazzer too?

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

Get started

Plug Slazzer into your agent.

Your users connect Slazzer once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.

Connect Slazzer Browse all apps →

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