> One governed access point for your AI across your systems, with the relations, permissions and prepared context only a cross-system layer can supply.

Source: https://www.smint.io/solutions/for-ai-platform  
Title: For AI Platform Teams: One Governed MCP Endpoint

---

# One governed experience layer for AI.

Sminted AI gives your AI one governed access point across all your systems, with the relations, permissions and prepared context that only a cross-system layer can supply. The single source of truth for your AI.

[Request a technical deep dive](https://www.smint.io/technical-deep-dive)[Sminted AI](https://www.smint.io/platform/sminted-ai)

-   [Sminted AI](https://www.smint.io/platform/sminted-ai)
-   [Unified Semantic Context Layer](https://www.smint.io/platform/uscl)
-   [Security](https://www.smint.io/security)

## One door for all your AI visitors

Connecting AI to your systems one by one means an integration each time, and permissions and context that stop at every system's edge. Sminted AI gives every AI assistant and agent one access point across all your connected systems.

### Governed by the same rules as your people

AI access runs through the same permission model as human access: the platform's own, with Dynamic Content Routing deriving who sees what from metadata, per market, per licence, per expiry. Evidenced by audit trails and SCIM.

### Context no single system holds

The endpoint knows how your systems relate, asset to product to market to rights, and serves content prepared for AI: permission-aware retrieval from one basis, not from ten systems one by one.

### Answered from the platform's own index

AI assistants and agents are served from the Unified Semantic Context Layer's own enriched index. Only original downloads reach your source systems, and we can host those originals too.

### Your AI, not ours

Connect your own models: AWS Bedrock, your own Claude, ChatGPT or Gemini accounts, or local models. Preparation runs once on cost-efficient models of your choice; your premium model is spent only on consuming refined context.

## With Sminted AI, your AI gets context, not files

An AI assistant or agent asking a Smint.io portal does not get a folder listing. It gets the asset with its product, its market, its usage rights and its expiry, prepared for machines: embeddings, summaries written for AI, and context drawn from inside the files themselves. It gets exactly what the portal user it acts for may see, across every connected system at once. And it gets it through a standard MCP server, so Claude, ChatGPT, Copilot, Cursor or your own agent framework connect without a plugin per tool.

[How Sminted AI works](https://www.smint.io/platform/sminted-ai)

## One endpoint per portal, authenticated your way

Every portal has its own MCP server, and there are two ways in. An AI assistant or agent can sign in as a portal user via OAuth and see exactly what that person sees. Or it runs as a service principal, a non-human identity with permissions of its own. Either way the same permission model applies, and every access is logged, human or AI. AI reads by default and writes where a component allows it.

## Try it on a real portal

Three public portals, each with its own MCP server. Just point your AI client at one, ask and see.

-   [
    
    ](https://new.oochiali.com)
    
    ### OOCHIALI Brand Portal
    
    Our fictional sunglass brand: collection sheets, campaign presentations, and the assets that are current rather than superseded.
    
    [How to connect your AI](https://www.smint.io/platform/sminted-ai#try-it)Connect your AI[Open portal](https://new.oochiali.com)
    
-   [
    
    ](https://documentation.smint.io)
    
    ### Smint.io Documentation Portal
    
    Our own product documentation, the portal our backend assistant reads: guides, tutorials and videos, 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://media.smint.io)
    
    ### Smint.io Media & Brand Portal
    
    Our own media center: product images, videos, webinars.
    
    [How to connect your AI](https://www.smint.io/platform/sminted-ai#try-it)Connect your AI[Open portal](https://media.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)

## 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 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)

## Where AI platform teams start

The experience for AI, the foundation beneath it, and the connectors into the systems your AI will work with.

[

### Sminted AI

The experience for AI: every portal an MCP endpoint, content prepared for machines, your own models.

](https://www.smint.io/platform/sminted-ai)[

### Unified Semantic Context Layer

The foundation: one semantic model over every connected system, the basis for people, AI and the API.

](https://www.smint.io/platform/uscl)[

### Security

SOC 2 Type II, SSO and SCIM, audit trails for human and AI access, self-hosting, what is stored and what is not.

](https://www.smint.io/security)

## Built on what runs in production

ArperFurniture design

Each region sees its own content through Dynamic Content Routing, the same permission model AI access runs on.

Global printing services companyAnonymized

Client portals operated in the provider's own VPC on AWS under strict isolation requirements.

Global luxury groupAnonymized

Several audiences on one platform, customer service, dealer shops and B2B, each a portal and so an endpoint of its own.

> Increasingly, your content is being read by AI assistants and agents. The question is whether they read it governed, from one semantic layer across all your systems, or scraped from ten of them one by one. We have the answer: Sminted AI gives every AI one cross-system context, the permissions of the user behind it, and content prepared for AI by AI.

Reinhard HolznerCEO & CTO, Smint.io

## Questions AI platform teams ask

Which permissions does an AI assistant or agent get?

Exactly those of the portal user it acts for. The platform's own permission system applies, including Dynamic Content Routing, which derives permissions from metadata. Pass-through authentication to a source system's permissions is possible where required.

How does AI authenticate?

Two ways. Delegated user identity via OAuth: the AI signs in as a portal user. Or a service principal with an assigned scope: a non-human identity with its own permissions. Both run through the same permission model, and both are standard MCP.

Can AI write, or only read?

Portal MCP servers read by default. Where a portal component supports it, uploads or requests for example, AI can also write, under the same permissions as a person using that component.

Which AI clients and models work?

Any MCP client: Claude, ChatGPT, Copilot, Cursor or your own agent framework, without a plugin per tool. The models are your choice: AWS Bedrock, your own Claude, ChatGPT or Gemini accounts, or local models. Preparation can run on your own models in your own cloud.

Is every AI access logged?

Yes. AI access appears in the audit trail beside human access.

## See AI working on your own content.

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