# Modelry AI integration on Definable

> Modelry is a 3D visualization platform for eCommerce that creates custom 3D product models, AR experiences, and digital asset management.

## What this connects

Modelry is a 3D visualization platform for eCommerce that creates custom 3D product models, AR experiences, and digital asset management.

Vendor: https://modelry.ai/

## Tools available

**14** tools available. First 12:

- `MODELRY_CREATE_WORKSPACE` — Create Workspace — Create a new workspace or return an existing one with the same name. Workspaces are used to organize products and embeds in Modelry. If workspace creation is not supported by the API, this tool will return an existing workspace matching the requested name.
- `MODELRY_DELETE_EMBED` — Delete Modelry Embed — Tool to delete an embed. Tries multiple common endpoint patterns and treats 404 as idempotent success after exhausting candidates (embed already deleted or not found).
- `MODELRY_DELETE_PRODUCT` — Delete Modelry Product — Permanently deletes a product from Modelry by its ID. Use this action to remove a product that is no longer needed. This operation is idempotent - deleting an already-deleted product will succeed without error. Prerequisites: - Obtain the product ID using MODELRY_LIST_PRODUCTS first - Ensure you have delete permissions for the product WARNING: This action is destructive and cannot be undone.
- `MODELRY_DELETE_PRODUCT_REPOSITORY` — Delete Product Repository — Permanently delete a product repository from Modelry. This action is idempotent - deleting a non-existent repository returns success. Use the list product repositories action first to get valid repository IDs.
- `MODELRY_DELETE_WORKSPACE` — Delete Modelry Workspace — Permanently deletes a Modelry workspace. This action is idempotent - deleting a non-existent workspace will return success. Use the list workspaces action first to get valid workspace IDs. WARNING: This is a destructive action that cannot be undone.
- `MODELRY_GET_EMBED` — Get Embed — Retrieve details of a specific Modelry embed (3D viewer or AR experience for eCommerce). Use MODELRY_LIST_EMBEDS first to obtain valid embed IDs. Returns embed metadata including status, workspace, and configuration details.
- `MODELRY_GET_WORKSPACE` — Get Workspace — Retrieves details for a specific Modelry workspace by its ID or name. The workspace ID can be obtained from the List Workspaces action. This action fetches all workspaces and returns the matching one.
- `MODELRY_LIST_EMBEDS` — List Embeds — List embeds in Modelry. Embeds are 3D viewer/AR embed codes for products. Use to retrieve embed IDs for downstream actions (e.g., MODELRY_GET_EMBED, MODELRY_DELETE_EMBED). Returns empty list if no embeds exist. Supports pagination and optional workspace filtering.
- `MODELRY_LIST_MODELING_REQUESTS` — List Modeling Requests — List all 3D modeling requests in a workspace. Requires workspace_id to scope the request. Returns modeling requests with their status and metadata.
- `MODELRY_LIST_PRODUCT_REPOSITORIES` — List Product Repositories — Tool to list all product repositories in a workspace. Use after confirming the workspace ID.
- `MODELRY_LIST_PRODUCTS` — List Modelry Products — List all products in Modelry. Returns paginated product data including IDs, names, and metadata. Use this to retrieve product IDs needed for other product-related actions like delete or get details. Optionally scope to a specific workspace using workspace_id parameter.
- `MODELRY_LIST_WORKSPACES` — List Modelry Workspaces — Tool to list all workspaces in Modelry. Use when you need to retrieve available workspaces after authenticating.

## Auth

Auth schemes: `API_KEY`.

## How agents use Modelry

Inside a Definable workflow, Modelry is one of the tools the **Distributor specialist** can call. Example coordination patterns:

- **Researcher → Modelry** — the Researcher (GPT-5.5) pulls context from Modelry (records, threads, documents), synthesises findings, and briefs the rest of the team.
- **Writer → Distributor → Modelry** — the Writer (Claude Opus 4.7) drafts copy in brand voice, the Verifier passes it, then the Distributor writes the result into Modelry (create record, post message, draft email).
- **Designer / Engineer → Distributor → Modelry** — the Designer ships an asset or the Engineer ships a code change, the Distributor delivers it via Modelry (attach file, open PR comment, post status).

The Verifier checks every Modelry call. On rate limit, schema drift, or auth refresh it self-heals and retries — the workflow completes without manual intervention.

## Categories

- ecommerce — https://definable.ai/apps/category/ecommerce/
- images & design — https://definable.ai/apps/category/images-&-design/

## Related

- HTML page: https://definable.ai/apps/modelry/
- Same category (ecommerce): https://definable.ai/apps/category/ecommerce/
- All integrations: https://definable.ai/apps/
- Workflow (multi-agent loop): https://definable.ai/workflow/
- Apps llms.txt index: https://definable.ai/llms-apps.txt