---
title: "Permissions"
description: "Integrated permission model for assistants, teams, and integrations"
canonical_url: "https://meingpt.com/en/docs/integrations/integration-permissions"
language: en
---

# Permissions

The second core topic besides the tool-call model is the integrated permission system.

## Core principle

- Assistants can be shared internally with **users and teams**
- Integrations/connections are attached to assistants in a controlled way
- Access remains traceable and secure even when assistants are shared

## Granularity by integration type

Permission control can apply on multiple levels:

- **Assistant level**: Who can use or edit an assistant?
- **Team level**: Which teams may use which integrations?
- **Connection level**: Which specific connection may be used by which assistant?

## Result

This model scales from simple team setups to strict enterprise governance requirements.

## Related docs

- [Core Concepts](/en/docs/integrations/integration-core-concept)
- [On-Premise Connections](/en/docs/integrations/connections-cloud-on-prem)
- [JWT Identity Forwarding](/en/docs/integrations/jwt-identity-forwarding)