> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oriant.app/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Tools

> Every AI tool found on your machines, with a sanction state per tool: Unsanctioned, Sanctioned or Blocked.

**AI Tools** lists every AI tool the agent has seen on your fleet: who uses it, on how many machines, when it was first and last seen, and the AI clients installed for it.

Each tool has one sanction state, and that state is the policy:

| State | What happens |
| - | - |
| **Unsanctioned** | The default for a newly found tool. Use is recorded and counted, not blocked. |
| **Sanctioned** | You trust it. Use is recorded, nothing else happens. |
| **Blocked** | You forbid it. The agent rejects connections to it on every machine. |

Blocking happens on the machine, so it works on any network.

Sanctioning a tool grants nothing on your MCP Connections. Which MCP tools a person may use is decided by [MCP Policies](https://docs.oriant.app/mcp-gateway/policies.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.