Cults for AI agents

Cults is a digital marketplace for 3D printing models, where independent designers list and sell files for people to print at home. 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.

E-commerceAPI keyMCP + RESTcults3d.com
AUDIT LOG · CULTSPOLICY: acme-support
09:41:07 · claude · u_8f2read
cults.get_approved_origins
Get Approved Origins✓ allowed · 212ms
09:41:09 · claude · u_8f2write
cults.graph_ql_post
Cults GraphQL POST✓ approved · approved by user
EVERY CULTS CALL, ON THE RECORD
01 · USE CASES

What agents do in Cults.

01

Query the marketplace catalog

Run a GraphQL query against Cults to look up a specific 3D model listing.

02

Check approved origins for embedding

Check which origins are approved before embedding a Cults listing on a site.

03

Share a new creation

Share a newly created model listing once a designer has uploaded it.

02 · ACTIONS

3 Cults actions, graded by risk.

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

read

1

Look things up. Allowed by default.

  • cults.get_approved_origins
    Get Approved Origins

write

2

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

  • cults.graph_ql_post
    Cults GraphQL POST
  • cults.share_on_create_fr
    Share on Create (FR)

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Cults in three steps.

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

Users add their Cults 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 Cults 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 Cults from any agent.

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

Cults and Arc0, answered.

Q01

Can I use Cults with Claude, ChatGPT or Cursor?

Yes. Connect Cults 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 Cults actions you allow.

Q02

How do users connect Cults?

Users add their Cults 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 Cults actions can my agent take?

3 in total: 1 read, 2 write and 0 destructive, such as “cults GraphQL POST”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Cults?

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

Q05

Can my own backend call Cults too?

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

Get started

Plug Cults into your agent.

Your users connect Cults once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.

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