​
Partnership

LlamaIndex has officially showcased their integration with Klavis AI in this LinkedIn post, demonstrating how to build AI agents that connect to MCP Servers in just a few lines of code.
LlamaIndex and Klavis Integration - Build AI agents that connect to MCP Servers

​
Prerequisites

Before we begin, you’ll need:

OpenAI API Key

Get your API key from OpenAI Platform (LlamaIndex uses OpenAI as the default LLM)

Klavis AI API Key

Get your API key from Klavis AI

​
Installation

First, install the required packages: 
pip install llama-index llama-index-tools-mcp klavis

​
Setup Environment Variables

import os

# Set environment variables
os.environ["OPENAI_API_KEY"] = "your-openai-api-key-here"    # Replace with your actual OpenAI API key
os.environ["KLAVIS_API_KEY"] = "your-klavis-api-key-here"   # Replace with your actual Klavis API key

​
Basic Setup

import os
from klavis import Klavis
from klavis.types import McpServerName
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import (
    BasicMCPClient,
    get_tools_from_mcp_url,
    aget_tools_from_mcp_url,
)

# Initialize clients
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
llm = OpenAI(model="gpt-4o-mini", api_key=os.getenv("OPENAI_API_KEY"))

​
Single Agent Integration

Let’s start with creating a simple AI agent that can summarize YouTube videos using LlamaIndex and Klavis MCP Server.

​
Step 1: Create MCP Server Instance

# Create a YouTube MCP server and get the server URL
youtube_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.YOUTUBE,
    user_id="1234",
    platform_name="Klavis",
)

youtube_mcp_server_url = youtube_mcp_instance.server_url
print(f"🔗 YouTube MCP server created at: {youtube_mcp_server_url}")

​
Step 2: Create LlamaIndex Agent with MCP Tools

from llama_index.core.agent.workflow import FunctionAgent

# Get tools from MCP server
youtube_tools = await aget_tools_from_mcp_url(
    youtube_mcp_server_url, 
    client=BasicMCPClient(youtube_mcp_server_url)
)

# Create agent with MCP-based tools
youtube_agent = FunctionAgent(
    name="youtube_agent",
    description="Agent using MCP-based tools",
    tools=youtube_tools,
    llm=llm,
    system_prompt="You are an AI assistant that uses MCP tools to analyze YouTube videos."
)

print("🤖 YouTube AI agent created successfully!")

​
Step 3: Use the Agent

YOUTUBE_VIDEO_URL = "https://www.youtube.com/watch?v=MmiveeGxfX0"  # pick a video you like!

response = await youtube_agent.run(f"Summarize this video: {YOUTUBE_VIDEO_URL}")
print("✅ Video Summary:", response)

​
Multi-Agent Workflow

Now let’s build a more sophisticated multi-agent workflow that summarizes YouTube videos and sends the summary via email.

​
Step 1: Create Multiple MCP Server Instances

import webbrowser

# Create YouTube MCP server
youtube_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.YOUTUBE,
    user_id="1234",
    platform_name="Klavis",
)

# Create Gmail MCP server with OAuth authorization
gmail_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.GMAIL,
    user_id="1234",
    platform_name="Klavis",
)

print("✅ Created YouTube and Gmail MCP instances")

# Open Gmail OAuth authorization
webbrowser.open(gmail_mcp_instance.oauth_url)
print(f"🔐 Opening OAuth authorization for Gmail, if you are not redirected, please open the following URL in your browser: {gmail_mcp_instance.oauth_url}")

​
Step 2: Create Multi-Agent Workflow

from llama_index.core.agent.workflow import FunctionAgent, AgentWorkflow

# Get MCP server URLs
youtube_mcp_server_url = youtube_mcp_instance.server_url
gmail_mcp_server_url = gmail_mcp_instance.server_url

# Get tools from both MCP servers
youtube_tools = await aget_tools_from_mcp_url(
    youtube_mcp_server_url, 
    client=BasicMCPClient(youtube_mcp_server_url)
)
gmail_tools = await aget_tools_from_mcp_url(
    gmail_mcp_server_url, 
    client=BasicMCPClient(gmail_mcp_server_url)
)

# Create specialized agents
youtube_agent = FunctionAgent(
    name="youtube_agent",
    description="Agent that can summarize YouTube videos",
    tools=youtube_tools,
    llm=llm,
    system_prompt="You are a YouTube video summarization expert. Use MCP tools to analyze and summarize videos.",
    can_handoff_to=["gmail_agent"],
)

gmail_agent = FunctionAgent(
    name="gmail_agent", 
    description="Agent that can send emails via Gmail",
    tools=gmail_tools,
    llm=llm,
    system_prompt="You are an email assistant. Use MCP tools to send emails via Gmail."
)

# Create multi-agent workflow
workflow = AgentWorkflow(
    agents=[youtube_agent, gmail_agent],
    root_agent="youtube_agent",
)

print("🤖 Multi-agent workflow created with YouTube and Gmail agents!")

​
Step 3: Run the Multi-Agent Workflow

YOUTUBE_VIDEO_URL = "https://www.youtube.com/watch?v=MmiveeGxfX0"  # pick a video you like!
EMAIL_RECIPIENT = "example@email.com"  # Replace with your email

resp = await workflow.run(
    user_msg=f"Summarize this video {YOUTUBE_VIDEO_URL} and send it to {EMAIL_RECIPIENT}"
)

print("\n✅ Workflow Result:", resp.response.content)

​
Next Steps

Explore More MCP Servers

Try other available servers like Slack, Notion, GitHub, etc.

Advanced Workflows

Build more complex multi-agent systems with branching logic

Custom Tools

Create custom tools and integrate them with your workflows

Production Deployment

Scale these patterns for production applications

​
Useful Resources

Happy building with LlamaIndex and Klavis! 🚀