How to integrate Refiner MCP with Codex

Codex is one of the most popular coding harnesses out there. And MCP makes the experience even better. With Refiner MCP integration, you can draft, triage, summarise emails, and much more, all without leaving the terminal or app, whichever you prefer.

Composio removes the Authentication handling completely from you. We handle the entire integration lifecycle, and all you need to do is just copy the URL below, authenticate inside Codex, and start using it.

Why use Composio?

Apart from a managed and hosted MCP server, you will get:

• CodeAct: A dedicated workbench that allows GPT to write its code to handle complex tool chaining. Reduces to-and-fro with LLMs for frequent tool calling.
• Large tool responses: Handle them to minimise context rot.
• Dynamic just-in-time access to 20,000 tools across 870+ other Apps for cross-app workflows. It loads the tools you need, so GPTs aren't overwhelmed by tools you don't need.

How to install Refiner MCP in Codex

Codex CLI

Run the command in your terminal.

This will auto-redirect you to the Rube authentication page.

Once you're authenticated, you will be able to access the tools.

Verify the installation by running:

codex mcp list

If you otherwise prefer to use config.toml, add the following URL to it. You can get the bearer token from rube.app → Use Rube → MCP URL → Generate token

[projects."/home/user/composio"]
trust_level = "untrusted"

[mcp_servers.rube]
bearer_token_env_var = "your bearer token"
enabled = true
url = "https://rube.app/mcp"

Codex in VS Code

If you have installed Codex in VS Code.

Then: ⚙️ → MCP Settings → + Add servers → Streamable HTTP:

Add the Rube MCP URL: https://rube.app/mcp and the bearer token.

To verify, click on the Open config.toml

Make sure it's there:

[mcp_servers.composio_rube]
bearer_token_env_var = "your bearer token"
enabled = true
url = "https://rube.app/mcp"

Codex App

Codex App follows the same approach as VS Code.

1. Click ⚙️ on the bottom left → MCP Servers → + Add servers → Streamable HTTP:

2. Restart and verify if it's there in .codex/config.toml

[mcp_servers.composio_rube]
bearer_token_env_var = "your bearer token"
enabled = true
url = "https://rube.app/mcp"

3. Save, restart the extension, and start working.

The Refiner MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Refiner account. It provides structured and secure access to your customer feedback and survey data, so your agent can perform actions like fetching contacts, analyzing survey responses, managing user segments, updating user data, and generating reports on your behalf.

• Contact management and updates: Effortlessly retrieve, update, or delete contact records, allowing your agent to keep user data clean and up-to-date.
• Survey and form discovery: Instantly list all surveys or forms in your Refiner account, filter by state, and access their configurations for deeper analysis or reporting.
• Survey response retrieval and analytics: Pull in all survey responses, filter results, and generate detailed analytics or reporting to uncover actionable insights from your customer feedback.
• User segmentation and targeting: Fetch and browse user segments, enabling your agent to target specific groups for outreach or further analysis based on collected data.
• Event tracking and behavioral logging: Automatically record user events, associate them with contacts, and enrich feedback data for advanced behavioral analytics.

Conclusion

You've successfully integrated Refiner with Codex using Composio's Rube MCP server. Now you can interact with Refiner directly from your terminal, VS Code, or the Codex App using natural language commands.

Key benefits of this setup:

• Seamless integration across CLI, VS Code, and standalone app
• Natural language commands for Refiner operations
• Managed authentication through Composio's Rube
• Access to 20,000+ tools across 870+ apps for cross-app workflows
• CodeAct workbench for complex tool chaining

Next steps:

• Try asking Codex to perform various Refiner operations
• Explore cross-app workflows by connecting more toolkits
• Build automation scripts that leverage Codex's AI capabilities