How to integrate Openai MCP with Claude Code

GET STARTED FOR FREE
Framework Integration Gradient
Openai Logo
Claude Code Logo
divider

Introduction

Manage your Openai directly from Claude Code with zero worries about OAuth hassles, API-breaking issues, or reliability and security concerns.

You can do this in two different ways:

  1. Via Rube - Direct and easiest approach
  2. Via Composio SDK - Programmatic approach with more control

Why Rube?

Rube is a universal MCP server with access to 850+ SaaS apps. It ensures just-in-time tool loading so Claude can access the tools it needs, a remote workbench for programmatic tool calling and handling large tool responses out of the LLM context window, ensuring the LLM context window remains clean.

Connect Openai to Claude Code with Rube

1. Get the MCP URL

Copy and paste the below command in Claude Code to add Rube MCP.

Terminal

2. Authenticate Rube

Run /mcp to view Rube

bash
/mcp
Run /mcp to view Rube in Claude Code
Click on Rube to authenticate
Authentication flow complete

3. Ensure it's connected

Run /mcp again to verify the connection. Now, do whatever you want with Claude Code and Openai.

Rube connected successfully

Supported Tools & Triggers

Tools
Create AssistantTool to create a new assistant with specified parameters.
Create MessageTool to create a new message in a specific thread.
Create ThreadTool to create a new thread.
Delete assistantTool to delete a specific assistant by its id.
Delete fileTool to delete a file.
List filesTool to retrieve a list of files.
List fine-tunesTool to list your organization's fine-tuning jobs.
List modelsTool to list available models.
List run stepsTool to retrieve all steps of a specific run.
Modify threadTool to modify an existing thread's metadata.
Retrieve assistantTool to retrieve details of a specific assistant.
Retrieve modelTool to retrieve details of a specific model.
Retrieve threadTool to retrieve details of a specific thread by its id.
Upload fileTool to upload a file for use across openai endpoints.

What is the Openai MCP server, and what's possible with it?

The Openai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your OpenAI account. It provides structured and secure access to your models, assistants, files, threads, and fine-tuning jobs, so your agent can perform actions like managing assistants, handling conversations, uploading or organizing files, and working with OpenAI models on your behalf.

  • Assistant and conversation management: Quickly create, update, or delete OpenAI assistants and manage threads or messages for seamless conversational flows.
  • File uploads and organization: Let your agent upload new files, list all uploaded documents, or delete unnecessary files to keep your workspace tidy.
  • Model discovery and utilization: Effortlessly list all available OpenAI models—including vision and multimodal—and retrieve their details to choose the best fit for your tasks.
  • Fine-tuning job insights: View a complete list of your organization's fine-tune jobs and track their progress or review results as needed.
  • Thread and run management: Create, modify, or inspect threads and run steps to fully control and monitor interactive agent conversations.

Connecting Openai via Tool Router

Tool Router is the underlying tech that powers Rube. It's a universal gateway that does everything Rube does but with much more programmatic control. You can programmatically generate an MCP URL with the app you need (here Openai) for even more tool search precision. It's secure and reliable.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Claude Pro, Max, or API billing enabled Anthropic account
  • Composio API Key
  • A Openai account
  • Basic knowledge of Python or TypeScript

Install Claude Code

bash
# macOS, Linux, WSL
curl -fsSL https://claude.ai/install.sh | bash

# Windows PowerShell
irm https://claude.ai/install.ps1 | iex

# Windows CMD
curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd

To install Claude Code, use one of the following methods based on your operating system:

Set up Claude Code

bash
cd your-project-folder
claude

Open a terminal, go to your project folder, and start Claude Code:

  • Claude Code will open in your terminal
  • Follow the prompts to sign in with your Anthropic account
  • Complete the authentication flow
  • Once authenticated, you can start using Claude Code
Claude Code initial setup showing sign-in prompt
Claude Code terminal after successful login

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here

Create a .env file in your project root with the following variables:

  • COMPOSIO_API_KEY authenticates with Composio (get it from Composio dashboard)
  • USER_ID identifies the user for session management (use any unique identifier)

Install Composio library

pip install composio-core python-dotenv

Install the Composio Python library to create MCP sessions.

  • composio-core provides the core Composio functionality
  • python-dotenv loads environment variables from your .env file

Generate Composio MCP URL

import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
USER_ID = os.getenv("USER_ID")

composio_client = Composio(api_key=COMPOSIO_API_KEY)

composio_session = composio_client.create(
    user_id=USER_ID,
    toolkits=["openai"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url

print(f"MCP URL: {COMPOSIO_MCP_URL}")
print(f"\nUse this command to add to Claude Code:")
print(f'claude mcp add --transport http openai-composio "{COMPOSIO_MCP_URL}" --headers "X-API-Key:{COMPOSIO_API_KEY}"')

Create a script to generate a Composio MCP URL for Openai. This URL will be used to connect Claude Code to Openai.

What's happening:
  • We import the Composio client and load environment variables
  • Create a Composio instance with your API key
  • Call create() to create a Tool Router session for Openai
  • The returned mcp.url is the MCP server URL that Claude Code will use
  • The script prints this URL so you can copy it

Run the script and copy the MCP URL

python generate_mcp_url.py

Run your Python script to generate the MCP URL.

  • The script connects to Composio and creates a Tool Router session
  • It prints the MCP URL and the exact command you need to run
  • Copy the entire claude mcp add command from the output

Add Openai MCP to Claude Code

bash
claude mcp add --transport http openai-composio "YOUR_MCP_URL_HERE" --headers "X-API-Key:YOUR_COMPOSIO_API_KEY"

# Then restart Claude Code
exit
claude

In your terminal, add the MCP server using the command from the previous step. The command format is:

  • claude mcp add registers a new MCP server with Claude Code
  • --transport http specifies that this is an HTTP-based MCP server
  • The server name (openai-composio) is how you'll reference it
  • The URL points to your Composio Tool Router session
  • --headers includes your Composio API key for authentication

After running the command, close the current Claude Code session and start a new one for the changes to take effect.

Verify the installation

bash
claude mcp list

Check that your Openai MCP server is properly configured.

  • This command lists all MCP servers registered with Claude Code
  • You should see your openai-composio entry in the list
  • This confirms that Claude Code can now access Openai tools

If everything is wired up, you should see your openai-composio entry listed:

Claude Code MCP list showing the toolkit MCP server

Authenticate Openai

The first time you try to use Openai tools, you'll be prompted to authenticate.

  • Claude Code will detect that you need to authenticate with Openai
  • It will show you an authentication link
  • Open the link in your browser (or copy/paste it)
  • Complete the Openai authorization flow
  • Return to the terminal and start using Openai through Claude Code

Once authenticated, you can ask Claude Code to perform Openai operations in natural language. For example:

  • "List all available OpenAI models"
  • "Upload a file for fine-tuning"
  • "Create a new assistant with GPT-4"

Complete Code

Here's the complete code to get you started with Openai and Claude Code:

import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
USER_ID = os.getenv("USER_ID")

composio_client = Composio(api_key=COMPOSIO_API_KEY)

composio_session = composio_client.create(
    user_id=USER_ID,
    toolkits=["openai"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url

print(f"MCP URL: {COMPOSIO_MCP_URL}")
print(f"\nUse this command to add to Claude Code:")
print(f'claude mcp add --transport http openai-composio "{COMPOSIO_MCP_URL}" --headers "X-API-Key:{COMPOSIO_API_KEY}"')

Conclusion

You've successfully integrated Openai with Claude Code using Composio's MCP server. Now you can interact with Openai directly from your terminal using natural language commands.

Key features of this setup:

  • Terminal-native experience without switching contexts
  • Natural language commands for Openai operations
  • Secure authentication through Composio's managed MCP
  • Tool Router for dynamic tool discovery and execution

Next steps:

  • Try asking Claude Code to perform various Openai operations
  • Add more toolkits to your Tool Router session for multi-app workflows
  • Integrate this setup into your development workflow for increased productivity

You can extend this by adding more toolkits, implementing custom workflows, or building automation scripts that leverage Claude Code's capabilities.

How to build Openai MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Openai MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Openai MCP with Claude Agent SDK

Google ADK

Google ADK

Use Openai MCP with Google ADK

LangChain

LangChain

Use Openai MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Openai MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Openai MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Openai MCP with LlamaIndex

CrewAI

CrewAI

Use Openai MCP with CrewAI

Codex

Codex

Use Openai MCP with Codex

FAQ

What are the differences in Tool Router MCP and Openai MCP?

With a standalone Openai MCP server, the agents and LLMs can only access a fixed set of Openai tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Openai and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Claude Code?

Yes, you can. Claude Code fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Openai tools.

Can I manage the permissions and scopes for Openai while using Tool Router?

Yes, absolutely. You can configure which Openai scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Openai data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free