> For the complete documentation index, see [llms.txt](https://help.meltingspot.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.meltingspot.io/english/manage-spot/integrations/ai-assistants-mcp/connect-openai-codex.md).

# Connect OpenAI Codex

Connect Codex to your Spot with the MeltingSpot plugin, or by adding the MCP server.

There are two ways to connect Codex to your Spot:

* **with the MeltingSpot plugin (recommended)**: the connection is already set up, and instructions guide Codex to use MeltingSpot properly;
* **by adding the MCP server by hand**.

Codex shares its configuration between the desktop app, the command line and the code editor extension: add MeltingSpot once and it is available everywhere.

Before you start, check the [prerequisites](https://help.meltingspot.io/english/manage-spot/integrations/ai-assistants-mcp.md#before-you-start): you are an administrator of the Spot and the MCP server is enabled for this Spot.

## Install the MeltingSpot plugin (recommended)

1. In a terminal, add the MeltingSpot marketplace:

   ```bash
   codex plugin marketplace add meltingspot/meltingspot-for-ai
   ```
2. In the Codex Plugins Directory, install `meltingspot` from the `meltingspot` marketplace.
3. Sign in to MeltingSpot when Codex asks you to: pick your Spot in **Spot to connect**, then click **Authorize**.

To learn more about what it contains, see [MeltingSpot plugin and skills](https://help.meltingspot.io/english/manage-spot/integrations/ai-assistants-mcp/meltingspot-plugin-and-skills.md).

## Or: add the server by hand

{% tabs %}
{% tab title="Desktop app" %}

1. Open **Settings > MCP servers**, then click **Add server**.
2. Choose **Streamable HTTP** and enter the server address:

   ```
   https://mcp.meltingspot.io/mcp
   ```
3. Save, then click **Restart**.
4. Click **Authenticate** next to MeltingSpot.
5. The MeltingSpot page opens in your browser: pick your Spot in **Spot to connect**, then click **Authorize**.
   {% endtab %}

{% tab title="Command line" %}

1. In a terminal, add the server:

   ```bash
   codex mcp add meltingspot --url https://mcp.meltingspot.io/mcp
   ```
2. Start the sign-in:

   ```bash
   codex mcp login meltingspot
   ```
3. The MeltingSpot page opens in your browser: pick your Spot in **Spot to connect**, then click **Authorize**.

To check that MeltingSpot is added: `codex mcp list`.
{% endtab %}
{% endtabs %}

## Use MeltingSpot

Make your request to Codex, for example: "List the groups of my Spot." In the desktop app, type `/mcp` in the message box to see the connected servers.

## Disconnect MeltingSpot

Remove MeltingSpot from **Settings > MCP servers**, or delete the `[mcp_servers.meltingspot]` block from the `~/.codex/config.toml` file.

{% hint style="info" %}
To work on another Spot, add a second server with the same address and another name, for example `meltingspot-academy`, then pick the other Spot on the MeltingSpot page.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.meltingspot.io/english/manage-spot/integrations/ai-assistants-mcp/connect-openai-codex.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
