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

# Using Codex with Marrow MCP

# Using Codex with Marrow MCP

Use Codex when you need an agent to generate or change code while reading live Marrow context through MCP.

<img src="https://mintlify.s3.us-west-1.amazonaws.com/hologrowinc/hub-files/mcp/marrow/codex-connector.png" alt="Codex connector setup steps" />

## Prerequisites

* [Codex CLI](https://github.com/openai/codex) installed and signed in to your account.
* A Marrow MCP key. Create one in [Marrow MCP Integrations](https://app.marrow.com/integrations/mcp).

## Step 1: Add the Marrow MCP server

Add this to `~/.codex/config.toml` (global) or `.codex/config.toml` (project-scoped):

```toml theme={null}
[mcp_servers.marrow]
url = "https://mcp.marrow.com/mcp/v1"
http_headers = { "marrow-mcp-key" = "YOUR_API_KEY" }
startup_timeout_sec = 30
```

Replace `YOUR_API_KEY` with your Marrow MCP key.

## Step 2: Reload Codex

Restart your Codex session so it loads the new MCP server.

## Step 3: Test the connection

Run a prompt that uses Marrow data, for example:

```text theme={null}
Show me my Amazon Seller Central sales for the last 7 days.
```

If Codex returns real data, you are connected.

## Starter project

Need a working starting point? Clone our [Codex template repository](https://github.com/Deltologic/marrow-mcp-codex). It ships preconfigured.

***

## Marrow MCP resources

Check the following resources for more information:

* MCP server URL: `https://mcp.marrow.com/mcp/v1`
* [Interactive Data Scheme](/hub/data-scheme)
* Data Scheme JSON: [https://api.marrow.com/api/v1/spec/data-scheme](https://api.marrow.com/api/v1/spec/data-scheme)
* Need help? Use the [contact form](https://forms.clickup.com/9015200219/f/8cnj2ev-38615/AOYF9I35QFOXWJQXIG?type=Form\&source=hub-mcp-codex-docs)