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

# Mattermost

Use Cortecs models with Mattermost Agents

[Mattermost](https://mattermost.com/) is a team collaboration platform. Its Agents plugin supports custom OpenAI-compatible services for AI conversations and summaries.

{% hint style="info" %}
Before you begin, create a Cortecs API key by following the [Member quickstart](/member-quickstart.md) and choose a tool-calling model from the [model catalog](https://cortecs.ai/serverlessModels).
{% endhint %}

## 1. Add Cortecs as a service

Open **System Console → Plugins → Agents**, select **Add a Service**, and enter:

| Field             | Value                                     |
| ----------------- | ----------------------------------------- |
| Name              | `Cortecs`                                 |
| Type              | **OpenAI Compatible**                     |
| API URL           | `https://api.cortecs.ai/v1`               |
| API Key           | Your Cortecs API key                      |
| Default Model     | The exact model ID from the model catalog |
| Use Responses API | Disabled for this Chat Completions setup  |

Save the service. For a Responses-based setup, see [API Compatibility](/api/api-compatibility.md) and enable only capabilities supported by your selected model and Cortecs endpoint.

## 2. Connect an agent

Open the **Agents** page and create or edit an agent. Select **Cortecs** as its **Service**, set a display name and username, and save.

Open a conversation with the agent and ask it to summarize a short piece of text. Check the [Cortecs Usage page](/web-console/usage.md) to confirm that the request reached Cortecs.

For more configuration options, see the [Mattermost provider guide](https://docs.mattermost.com/agents/docs/providers).