> Serve your content to Claude, ChatGPT, Copilot or any MCP client as prepared context, from one governed data basis across all your systems.

Source: https://www.smint.io/platform/sminted-ai  
Title: Sminted AI: The Governed Experience Layer for AI

---

# The governed experience layer for AI.  
Sminted AI.

Sminted AI serves your content and information to AI as prepared context, from one consolidated, contextualized and governed data basis across all your systems.

[Request a demo](https://www.smint.io/demo)[How it works](#one-source-of-truth)

-   [Platform](https://www.smint.io/platform)
-   [Portals](https://www.smint.io/platform/portals)
-   [Unified Semantic Context Layer](https://www.smint.io/platform/uscl)

## One single source of truth

Sminted AI brings together your portal context, the guidelines, documentation and relations that exist in no other system, with your external data. From that one governed, agent-ready context it serves humans and AI alike.

### Your existing systems

-   DAM
-   PIM
-   ECM / SharePoint
-   CMS
-   MRM
-   Custom systems

### Sminted AI

**The experience for AI**

MCP · agent-ready context, governed per principal.

-   PortalsGuidelines and content contextualizing your content
-   Unified Semantic Context LayerExternal data, consolidated into one semantic model

-   You are hereSminted AIWhere things come together: one MCP server per portal

### Humans via MCP

-   Site search
-   Office
-   Creative tools

### AI via MCP

-   AI agents
-   AI assistants

## Everything your AI needs to act

AI needs to know how things relate, what it may see, and to get answers without waiting.

### Relations

Your DAM knows assets, your PIM knows products, your ERP knows orders. Sminted AI knows that _this_ asset belongs to _that_ product in _this_ market under _that_ usage restriction. These connections live between systems, not inside any one of them.

### Portal context

Your portal shows what your teams approved for that specific audience, and all the guidance they wrote around it. Sminted AI answers the way your portal would, because it reads your portal.

### Governance

AI access runs through the same permission model as your people, for example per market, per license or per expiry. Two colleagues asking the same question get different answers, because their permissions differ.

### Speed, resilience

Answers come from the Unified Semantic Context Layer's prepared index, with no live load on your source systems and no quota limits.

Sminted AI complements your source systems: each keeps its own domain, and the layer above adds what only a cross-system view can.

## Realize significant token savings

Sminted AI prepares content up front: embeddings, summaries written for AI, and context. **It even reads inside files to capture their meaning.** Your AI clients consume ready context instead of assembling it. One connection instead of many also means smaller context windows and faster answers.

Preparation runs once, on cost-efficient models, with caching that avoids repeated token use. Your premium model is spent only on consuming refined context, prepared once and amortized across every query.

“Use your own AI” covers preparation too. Those models can be your own, running in your own cloud. Your content never passes through an inference provider you didn't choose.

## Wherever your teams work, your content is there

Sminted AI is a standard MCP server, so any MCP client can consume it without per-tool plugins. Same content, same permissions, no download-and-re-upload detour.

### AI assistants

“Which product shots may we still use in Germany, and until when?” Answered from your own content, with that person's permissions.

### Office

The current product description and the approved image, straight into the proposal deck.

### Creative tools

The rights-cleared master for the market you're designing for, instead of a copy someone emailed last quarter.

## AI in the product, not next to it

### AI site search

Visitors chat with your content instead of paging through result lists: the built-in RAG application on the governed retrieval layer.

### Semantic and visual search

Natural-language queries and reverse image search across everything the layer indexes. In production at a global jewelry company.

### AI-enriched metadata

Asset analysis, automatic metadata extraction and OCR make content findable without manual tagging, including the text inside PDFs.

### Use your own AI

Connect your own models, AWS Bedrock, your own Claude, ChatGPT or Gemini accounts, or local models, for consuming refined context and for preparing it. Your data, your model choice.

[How enrichment and search work](https://www.smint.io/platform/uscl)

## Try it on a real portal

Open a portal in your browser, or connect your AI assistant to it and ask it something.

-   [
    
    ](https://media.smint.io)
    
    ### Smint.io Media & Brand Portal
    
    Our own media and brand portal.
    
    [How to connect your AI](https://www.smint.io/platform/sminted-ai#try-it)Connect your AI[Open portal](https://media.smint.io)
    
-   [
    
    ](https://documentation.smint.io)
    
    ### Smint.io Documentation Portal
    
    The Smint.io documentation, readable by your AI client.
    
    [How to connect your AI](https://www.smint.io/platform/sminted-ai#try-it)Connect your AI[Open portal](https://documentation.smint.io)
    
-   [
    
    ](https://new.oochiali.com)
    
    ### OOCHIALI Brand Portal
    
    A demo brand portal you can explore freely.
    
    [How to connect your AI](https://www.smint.io/platform/sminted-ai#try-it)Connect your AI[Open portal](https://new.oochiali.com)
    

## Connect your AI to the Smint.io Media & Brand Portal

It is easy, and it takes only about a minute.

ClaudeChatGPTMicrosoft CopilotOther MCP client

1.  1
    
    [Create your portal user account first](https://media.smint.io/Account/Register)
    
2.  2
    
    Add a new connector
    
    In Claude, open **Customize → Connectors**, select **\+ Add** and choose **Add custom connector**.
    
    In ChatGPT, open **Plugins**, select **+** and choose **Add custom MCP server**.
    
    In Copilot Studio, add a **tool** to your agent and choose **Model Context Protocol**. The agent needs generative orchestration turned on.
    
    In any MCP client, add a **remote MCP server** (Streamable HTTP).
    
3.  3
    
    Paste this address
    
    `https://media.smint.io/mcp`CopyCopied
    
4.  4
    
    Asked for a client ID? Use this one
    
    `smintio-mcp`CopyCopied
    
5.  5
    
    Sign in and approve
    
    Your AI client opens the portal's sign-in. Sign in with that account and approve the connection.
    
6.  6
    
    Try asking something, for example
    
    -   “Find our current logo as SVG.”
    -   “What are the Smint.io brand colours?”
    -   “Show me the Portals promo videos.”
    

[How Sminted AI works](https://www.smint.io/platform/sminted-ai)[Open the portal in your browser](https://media.smint.io)

## Connect your AI to the Smint.io Documentation Portal

It is easy, and it takes only about a minute.

ClaudeChatGPTMicrosoft CopilotOther MCP client

1.  1
    
    [Create your portal user account first](https://documentation.smint.io/Account/Register)
    
2.  2
    
    Add a new connector
    
    In Claude, open **Customize → Connectors**, select **\+ Add** and choose **Add custom connector**.
    
    In ChatGPT, open **Plugins**, select **+** and choose **Add custom MCP server**.
    
    In Copilot Studio, add a **tool** to your agent and choose **Model Context Protocol**. The agent needs generative orchestration turned on.
    
    In any MCP client, add a **remote MCP server** (Streamable HTTP).
    
3.  3
    
    Paste this address
    
    `https://documentation.smint.io/mcp`CopyCopied
    
4.  4
    
    Asked for a client ID? Use this one
    
    `smintio-mcp`CopyCopied
    
5.  5
    
    Sign in and approve
    
    Your AI client opens the portal's sign-in. Sign in with that account and approve the connection.
    
6.  6
    
    Try asking something, for example
    
    -   “Which SSO providers are supported?”
    -   “How do I require approval before a download?”
    -   “What is Dynamic Content Routing?”
    

[How Sminted AI works](https://www.smint.io/platform/sminted-ai)[Open the portal in your browser](https://documentation.smint.io)

## Connect your AI to the OOCHIALI Brand Portal

It is easy, and it takes only about a minute.

ClaudeChatGPTMicrosoft CopilotOther MCP client

1.  1
    
    [Create your portal user account first](https://new.oochiali.com/Account/Register)
    
2.  2
    
    Add a new connector
    
    In Claude, open **Customize → Connectors**, select **\+ Add** and choose **Add custom connector**.
    
    In ChatGPT, open **Plugins**, select **+** and choose **Add custom MCP server**.
    
    In Copilot Studio, add a **tool** to your agent and choose **Model Context Protocol**. The agent needs generative orchestration turned on.
    
    In any MCP client, add a **remote MCP server** (Streamable HTTP).
    
3.  3
    
    Paste this address
    
    `https://new.oochiali.com/mcp`CopyCopied
    
4.  4
    
    Asked for a client ID? Use this one
    
    `smintio-mcp`CopyCopied
    
5.  5
    
    Sign in and approve
    
    Your AI client opens the portal's sign-in. Sign in with that account and approve the connection.
    
6.  6
    
    Try asking something, for example
    
    -   “Show me the OOCHIALI colour palette.”
    -   “Which logo variants may I use on a dark background?”
    -   “What is in the Live freely campaign?”
    

[How Sminted AI works](https://www.smint.io/platform/sminted-ai)[Open the portal in your browser](https://new.oochiali.com)

## Your portals are already agent-ready

Sminted AI is live, and every portal you run is agent-ready automatically. See it working on your own content.

[Request a demo](https://www.smint.io/demo)
