Open In Colab

​
OpenAI + Klavis AI Integration

This tutorial demonstrates how to use OpenAI function calling with Klavis MCP (Model Context Protocol) servers.

​
Prerequisites

Before we begin, you’ll need:

OpenAI API Key

Get your API key from OpenAI Platform

Klavis AI API Key

Get your API key from Klavis AI

​
Installation

First, install the required packages: 
pip install openai klavis requests

​
Setup Environment Variables

import os
import json
from openai import OpenAI
from klavis import Klavis
from klavis.types import McpServerName, ToolFormat

# Set environment variables
os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY"  # Replace with your actual OpenAI API key
os.environ["KLAVIS_API_KEY"] = "YOUR_KLAVIS_API_KEY"  # Replace with your actual Klavis API key

​
Case Study 1: OpenAI + YouTube MCP Server

​
Step 1 - Create YouTube MCP Server using Klavis

klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))

youtube_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.YOUTUBE,
    user_id="1234"
)

# print(f"🔗 YouTube MCP server created at: {youtube_mcp_instance.server_url}, and the instance id is {youtube_mcp_instance.instance_id}")

​
Step 2 - Create general method to use MCP Server with OpenAI

def openai_with_mcp_server(mcp_server_url: str, user_query: str):
    openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

    messages = [
        {"role": "system", "content": "You are a helpful assistant. Use the available tools to answer the user's question."},
        {"role": "user", "content": f"{user_query}"}
    ]
    
    mcp_server_tools = klavis_client.mcp_server.list_tools(
        server_url=mcp_server_url,
        format=ToolFormat.OPENAI
    )
    
    response = openai_client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages,
        tools=mcp_server_tools.tools
    )
    
    messages.append(response.choices[0].message)

    if response.choices[0].message.tool_calls:
        for tool_call in response.choices[0].message.tool_calls:
            function_name = tool_call.function.name
            function_args = json.loads(tool_call.function.arguments)
            
            print(f"🔧 Calling: {function_name}, with args: {function_args}")
            
            result = klavis_client.mcp_server.call_tools(
                server_url=mcp_server_url,
                tool_name=function_name,
                tool_args=function_args
            )
            
            messages.append({
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": str(result)
            })
            
    final_response = openai_client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages
    )
    
    return final_response.choices[0].message.content

​
Step 3 - Summarize your favorite video!

YOUTUBE_VIDEO_URL = "https://www.youtube.com/watch?v=LCEmiRjPEtQ"  # pick a video you like!

result = openai_with_mcp_server(
    mcp_server_url=youtube_mcp_instance.server_url, 
    user_query=f"Summarize this YouTube video with timestamps: {YOUTUBE_VIDEO_URL}"
)

print(result)
✅ Great! You’ve successfully created an AI agent that uses OpenAI function calling with Klavis MCP servers to summarize YouTube videos!

​
Case Study 2: OpenAI + Gmail MCP Server (OAuth needed)

import webbrowser

gmail_mcp_server = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.GMAIL,
    user_id="1234"
)

webbrowser.open(gmail_mcp_server.oauth_url)

print(f"🔐 Opening OAuth authorization for Gmail, if you are not redirected, please open the following URL in your browser: {gmail_mcp_server.oauth_url}")
After completing the OAuth authorization, you can send emails using the agent.
EMAIL_RECIPIENT = "zihaolin@klavis.ai" # Replace with your email
EMAIL_SUBJECT = "Test OpenAI + Gmail MCP Server"
EMAIL_BODY = "Hello World"

result = openai_with_mcp_server(
    mcp_server_url=gmail_mcp_server.server_url, 
    user_query=f"Please send an email to {EMAIL_RECIPIENT} with subject {EMAIL_SUBJECT} and body {EMAIL_BODY}"
)

print(result)

​
Summary

This tutorial demonstrated how to integrate OpenAI’s function calling capabilities with Klavis MCP servers to create powerful AI applications. We covered two practical examples: 🎥 YouTube Integration: Built an AI assistant that can automatically summarize YouTube videos by extracting transcripts and providing detailed, timestamped summaries. 📧 Gmail Integration: Created an AI-powered email assistant that can send emails through Gmail with OAuth authentication.

​
Key Takeaways:

  • Easy Setup: Klavis MCP servers can be created with just a few lines of code
  • OpenAI Compatible: All tools are formatted for seamless OpenAI function calling
  • Versatile: Support for both simple APIs (YouTube) and OAuth-authenticated services (Gmail)
  • Scalable: The same pattern can be applied to any of the MCP servers available in Klavis

​
Next Steps

Explore More MCP Servers

Try other available servers like Notion, Salesforce, Google Drive, etc.

Build Complex Workflows

Create sophisticated agents that combine multiple services

Production Deployment

Scale these patterns for production applications

Custom MCP Servers

Build your own MCP servers for custom integrations

​
Useful Resources

Happy building! 🚀