> For the complete documentation index, see [llms.txt](https://docs.strongdm.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.strongdm.com/ai/ai.md).

# Secure AI

StrongDM extends its access controls, credential isolation, and audit trail to AI agents.

Secure agent-to-resource access through controlled MCP connections, preserve least-privilege entitlements, and identify AI-initiated activity. Use these capabilities to govern agent access without exposing credentials or weakening existing controls.

### MCP Gateway

Proxy streamable HTTP MCP servers through StrongDM. Centralize authentication, authorization, credential management, and audit enforcement for each MCP tool invocation.

<a href="/ai/mcp-gateway.md" class="button primary">Learn more about MCP Gateway</a>

***

### MCP Broker for Desktop AI Agents

{% hint style="warning" %}
This feature is currently in closed-access technical preview. Functionality and documentation may change. Contact StrongDM for more information.
{% endhint %}

Learn how to allow desktop AI agents to access entitled resources through the MCP Broker. Agents receive credential-less, fully audited access to approved databases, servers, and clusters using the user's entitlements.

<a href="/ai/mcp-broker.md" class="button primary">MCP Broker</a>

***

### MCP Broker Administration

{% hint style="warning" %}
This feature is currently in closed-access technical preview. Functionality and documentation may change. Contact StrongDM for more information.
{% endhint %}

Govern and enforce AI-agent access through the deployment of MCP Broker.

<a href="/ai/mcp-broker-administration.md" class="button primary">Learn more about deploying MCP Broker to clients</a>

***

### AI Attribution

{% hint style="warning" %}
This feature is currently in closed-access technical preview. Functionality and documentation may change. Contact StrongDM for more information.
{% endhint %}

Detect supported AI tools in resource sessions and queries. Use initiator data in policies to apply more precise controls to agentic access.

<a href="/ai/ai-attribution.md" class="button primary">AI Attribution</a>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.strongdm.com/ai/ai.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.