Skip to content

Product data integration

Product data integration that stays yours.

Your agencies build the apps. Your data model shouldn't live in their code.

For IT and digital leads at manufacturers and distributors who run the apps their agencies build.

Runs on your infrastructure or ours. The Console has a free tier.

In production at industrial companies since 2022, from steel to eyewear.

  • voestalpine
  • Mehler Elektrotechnik
  • STRASSER Steine
  • LiSEC
  • Silhouette
  • Lumeso
The problem

Your data lives in exports. Every new app and every agent starts from scratch.

  • Scattered

    PIM, ERP and Excel exports, each in its own shape. Nobody has the whole picture.

  • Dependent

    The integration lives in one agency's code. A new partner or a new app means starting over.

  • Unreadable

    Your own AI agents get raw files or nothing. No model, no types, no clear access.

Why

The hard part of an app was never the code. It's the data.

Your product data should work for every app and every agent you run. Not only for the one built last. The data is yours. The model that makes it usable should be too: in your house, readable by your people and by your agents.

How

One tested model, in your house, open to your agents

  1. Exports become one model

    Workflows load, join and check your exports into a typed model with quality rules, tested before release.

  2. On your infrastructure

    Workflow and REST runtime on your own servers, or hosted in the dcupl Console. Your choice per application.

  3. Read-only for agents

    Your agents query the model via MCP with the application's key, where it is turned on. They can read, not change.

The Data Explorer in the dcupl Console, on demo data. Try the filters.

Data Explorerdcupl Console
Model ProductDemo data
No filters. Pick a facet.
Products, filtered by the selected facets
id, stringkeyname, stringcategory, stringprice, floatonSale, boolean
SKU-1001 NYM-J cable 3x1.5, 50 m Cable €42.90 false
SKU-1002 NYM-J cable 5x2.5, 50 m Cable €118.00 false
SKU-1003 Flat cable 3x1.5, 25 m Cable €24.50 true
SKU-2001 Rocker switch, white Switch €6.90 true
SKU-2002 LED dimmer switch, white Switch €48.00 false
SKU-2003 Two-way switch, anthracite Switch €14.20 true
SKU-3001 LED panel 600x600, 36 W Lighting €89.00 false
SKU-3002 LED downlight, 7 W Lighting €12.40 true
1–8 of 12 rows price · avg €51.18

What

What your teams see, and what your agents query

Agent access via MCP

The same model via MCP

Switch it on and a deployed application can be an MCP server. One URL, the application's existing API key, seven read-only tools.

  • models
  • query
  • aggregate
  • facet
  • pivot
  • metadata
  • suggest

Seven read-only tools, plus one endpoint_* tool per scripted endpoint of your API.

MCP endpoint in the docs
MCP config in your agentJSON
{
  "mcpServers": {
    "dcupl-product-data": {
      "type": "http",
      "url": "https://<runner>/instance/<key>/mcp",
      "headers": { "api-key": "<api key>" }
    }
  }
}

What IT leads ask

Who sees what?

A REST API instance is protected by the API key in its template. Without one it is open to anyone who has the URL. Whoever holds the key can query all the data that instance serves, over REST and over MCP where it is turned on. To give a group less, give it its own application and its own REST API with its own key.

Models and workflows are files you own, and the SDK and the CLI are free on npm. Another partner agency can take over.

  • voestalpine
    500,000+
    orders, 5+ million documents
  • Mehler Elektrotechnik
    11,000+
    items in the product search
  • STRASSER Steine
    30,000+
    sinks, hobs and extractor fans to configure a worktop
  • LiSEC
    myLiSEC
    customer portal

Workflows, REST API instances, MCP and hosting are covered by a Console plan. What each plan includes: dcupl pricing →

Latest insights

All insights →
Three rows, each with a change, a staged state and a production state: the CLI with built false and dcupl app build, a workflow variant and promote to base, and a REST API instance with status updating.

NewInsight · Data governance · November 5, 2026

Stage, build, approve: why nothing in dcupl happens by surprise

The CLI stages before it builds. A workflow variant runs on a dev runner before it is promoted. An API instance serves the old data until the update is done. One rule, three places, and why it matters when agents write the changes.

Talk to a customer who runs it.