Get started

Modelry for AI agents

Modelry is a 3D visualization platform for e-commerce that creates 3D product models and AR experiences for online stores selling physical goods. 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 ModelrySee the 14 actions ↓
E-commerceAPI keyMCP + RESTmodelry.ai
AUDIT LOG · MODELRYPOLICY: acme-support
09:41:07 · claude · u_8f2read
modelry.list_embeds
List Embeds✓ allowed · 212ms
09:41:08 · claude · u_8f2read
modelry.get_embed
Get Embed✓ allowed · 164ms
09:41:09 · claude · u_8f2write
modelry.create_workspace
Create Workspace✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
modelry.delete_embed
Delete Modelry Embed✕ blocked · policy: deny
EVERY MODELRY CALL, ON THE RECORD
01 · USE CASES

What agents do in Modelry.

01

Check a modeling request's progress

Track the progress of a submitted 3D modeling order, a read-only status check.

02

List products in a repository

List the 3D products stored in a repository before adding one to a product page.

03

Approve before deleting a workspace

Require approval before deleting a workspace, since it removes its products and embeds.

02 · ACTIONS

14 Modelry actions, graded by risk.

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

read

8

Look things up. Allowed by default.

  • modelry.get_embed
    Get Embed
  • modelry.list_embeds
    List Embeds
  • modelry.get_workspace
    Get Workspace
  • modelry.list_products
    List Modelry Products
  • modelry.list_workspaces
    List Modelry Workspaces
  • modelry.list_modeling_requests
    List Modeling Requests
  • modelry.list_product_repositories
    List Product Repositories
  • modelry.track_modeling_progress
    Track Modeling Progress

write

2

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

  • modelry.create_workspace
    Create Workspace
  • modelry.order_modeling_service
    Order Modeling Service

destructive

4

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

  • modelry.delete_embed
    Delete Modelry Embed
  • modelry.delete_product
    Delete Modelry Product
  • modelry.delete_workspace
    Delete Modelry Workspace
  • modelry.delete_product_repository
    Delete Product Repository
03 · HOW IT WORKS

Modelry in three steps.

  1. 01Your users connect ModelryThey add their Modelry api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Workspace” can wait for the user, and “delete Modelry Embed” can be denied outright.
  3. 03Any agent can actYour agent calls Modelry 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('modelry', {
  read: 'allow',
  write: 'ask',        // create_workspace
  destructive: 'deny',  // delete_embed
})

# 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 Modelry connects.

Users add their Modelry 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 Modelry 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 Modelry from any agent.

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

More e-commerce apps.

Shopify407 actionsAlpaca100 actionsClover209 actionsCloudcart150 actionsBaselinker106 actionsShippo95 actionsShipengine66 actionsProabono64 actions
ALL E-COMMERCE APPS →
07 · FAQ

Modelry and Arc0, answered.

Q01

Can I use Modelry with Claude, ChatGPT or Cursor?

Yes. Connect Modelry 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 Modelry actions you allow.

Q02

How do users connect Modelry?

Users add their Modelry 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 Modelry actions can my agent take?

14 in total: 8 read, 2 write and 4 destructive, such as “create Workspace”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Modelry?

Yes. Actions like “delete Modelry Embed” 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 Modelry too?

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

Get started

Plug Modelry into your agent.

Your users connect Modelry once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

Connect ModelryBrowse all apps →

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