> ## Documentation Index
> Fetch the complete documentation index at: https://help.desk.min-ai.ar/llms.txt
> Use this file to discover all available pages before exploring further.

# Connectors

> Connect your company's API or an MCP server so agents can look up stock, orders or customers, with the policy you choose for each action.

A **connector** gives your agents access to one of your company's systems: your own **HTTP API** or an **MCP server**. Each thing the agent can do there is an **action**, and each action has its policy: whether it runs on its own, the customer confirms it or the team approves it.

The URL and the key stay on the app's side: **the agent never sees them**.

## Creating a connection

In **Connectors**, tap **New connection**:

* **Name**: for example, Orders system.
* **MCP server URL** (Streamable HTTP, over HTTPS) or **API base URL** (HTTPS and public hosts only; actions add their path to this URL).
* **Authentication**: **No authentication**, **Token (Bearer)**, **Username and password**, **Key in a header** or **OAuth2 (client credentials)**. Secrets are stored encrypted and never shown again.

## Actions

**MCP server**

Tap **Read tools**: each of the server's tools shows up as an action, **turned off**. Review it, pick its policy and enable it.

If the server changes, tap **Read tools** again. New ones are added; changed ones are marked **Changed on the server** until you review them; the ones that are gone are turned off.

**HTTP API**

Tap **New action** to build one by hand, or **Import OpenAPI** to paste an OpenAPI document (JSON or YAML): each operation becomes an action, turned off, reads automatic and changes confirmed by the customer.

In the **Request**, use `{{field}}` for what the agent fills in, and `{{contact.phone}}`, `{{contact.email}}` or `{{contact.name}}` for the conversation's customer: the app sets those and the agent can't change them.

On each action:

* **For the agent**: its **Name** (lowercase, numbers and \_, like `check_stock`) and **When to use it**: what it does, when it helps and what it returns. Without a description, the agent won't know when to use it.
* **When it runs**: the policy (see below).
* **Data the agent fills in**: a JSON Schema (on MCP, defined by the server).
* **Response**: the **Fields it reads** (one path per line, like `order.status` or `items[].price`), the **Maximum items** and the **Maximum wait (s)**. Less is better: faster, cheaper and no extra data.
* **Test**: runs the action with test data and shows what the agent would read. If the action changes your system, the test really does it.

## Policies

| Policy | What happens |
| - | - |
| **Automatic** | The agent uses it when it's needed. |
| **The customer confirms** | The agent explains what it will do and waits for their yes in the conversation. |
| **The team approves** | It waits for someone on the team to approve it; the agent tells the customer how it went. See [Approvals](https://help.desk.min-ai.ar/en/serve/approvals.md). |

> [!WARNING]
>
> An action that **changes** your system with the **Automatic** policy runs without anyone confirming it. Use this only if it's harmless.

## Giving actions to an agent

An enabled action isn't used by anyone yet: on the agent, **Tools → Actions in your systems**, turn on the ones it may use. See [Agents](https://help.desk.min-ai.ar/en/setup/agents.md#tools).


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