MuAPI for AI agents

MuAPI is an OpenAI-compatible API for generating images and discovering which image generation models are supported, letting teams switch models easily. 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.

AI and modelsAPI keyMCP + RESTmuapi.ai
AUDIT LOG · MUAPIPOLICY: acme-support
09:41:07 · claude · u_8f2read
muapi.list_models
List Models✓ allowed · 212ms
09:41:08 · claude · u_8f2read
muapi.get_catalog_model
Get Catalog Model✓ allowed · 164ms
09:41:09 · claude · u_8f2write
muapi.generate_image
Generate Image✓ approved · approved by user
EVERY MUAPI CALL, ON THE RECORD
01 · USE CASES

What agents do in MuAPI.

01

Generate an image from a prompt

Create a draft image from a text prompt for a creative concept.

02

Check available models

List the models supported through the catalog before choosing one for a job, read-only.

03

Estimate cost before generating

Estimate the cost of an image generation request before submitting it, so spend stays predictable.

02 · ACTIONS

5 MuAPI actions, graded by risk.

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

read

4

Look things up. Allowed by default.

  • muapi.list_models
    List Models
  • muapi.get_catalog_model
    Get Catalog Model
  • muapi.list_catalog_models
    List Catalog Models
  • muapi.estimate_model_cost
    Estimate Model Cost

write

1

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

  • muapi.generate_image
    Generate Image

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

MuAPI in three steps.

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

Users add their MuAPI 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 MuAPI 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 MuAPI from any agent.

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

MuAPI and Arc0, answered.

Q01

Can I use MuAPI with Claude, ChatGPT or Cursor?

Yes. Connect MuAPI 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 MuAPI actions you allow.

Q02

How do users connect MuAPI?

Users add their MuAPI 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 MuAPI actions can my agent take?

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

Q04

Can I make my agent read-only in MuAPI?

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

Q05

Can my own backend call MuAPI too?

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

Get started

Plug MuAPI into your agent.

Your users connect MuAPI once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.

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