# Collection-Based RBAC

Admins can grant users access to specific agent or MCP collections, providing granular control for dev teams and security teams.

## How It Works

* Assign users to specific collections (agent or MCP)
* Users only see and can manage their assigned collections
* Useful for team separation and compliance

## Use Cases

* **Team Isolation**: Give each team access to their own agents
* **Environment Control**: Restrict production agent access
* **Compliance**: Limit sensitive agent access to authorized users
* **MCP Security**: Control who can manage high-risk MCP servers

## Setting Up RBAC

1. Navigate to **Settings > Users & Roles**
2. Select a user or role
3. Assign specific agent/MCP collections
4. Set permissions (view, edit, scan, delete)


---

# Agent Instructions: 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:

```
GET https://ai-security-docs.akto.io/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-ai-discovery/how-to/collection-based-rbac.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.