How to integrate Affinda MCP with Codex

Codex is one of the most popular coding harnesses out there. And MCP makes the experience even better. With Affinda 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 Affinda 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 Affinda MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Affinda account. It provides structured and secure access to your document processing workflows, so your agent can upload files, extract data, organize workspaces, label documents, and automate annotation management on your behalf.

• AI-powered document upload and extraction: Instantly have your agent upload new documents for parsing and extract structured data from various formats using Affinda's advanced AI models.
• Workspace and collection management: Let your agent create, group, and organize documents into collections and workspaces, keeping your document processing streamlined and organized.
• Automated annotation updates: Empower your agent to batch update or modify multiple document annotations in a single request, saving you time on manual corrections.
• Document tagging and organization: Direct your agent to create tags and label documents, making it easy to categorize and quickly retrieve important files.
• Effortless cleanup and resource management: Have your agent delete unwanted documents or collections, ensuring your Affinda account stays tidy and relevant at all times.

Conclusion

You've successfully integrated Affinda with Codex using Composio's Rube MCP server. Now you can interact with Affinda 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 Affinda 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 Affinda operations
• Explore cross-app workflows by connecting more toolkits
• Build automation scripts that leverage Codex's AI capabilities