Skip to main content

​
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

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"))

​
Step 1 - Create Strata MCP Server with Gmail and Slack

from klavis import Klavis
from klavis.types import McpServerName, ToolFormat
import webbrowser

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

response = klavis_client.mcp_server.create_strata_server(
    servers=[McpServerName.GMAIL, McpServerName.SLACK], 
    user_id="1234"
)

# Handle OAuth authorization for each services
if response.oauth_urls:
    for server_name, oauth_url in response.oauth_urls.items():
        webbrowser.open(oauth_url)
        print(f"Or please open this URL to complete {server_name} OAuth authorization: {oauth_url}")
OAuth Authorization Required: The code above will open browser windows for each service. Click through the OAuth flow to authorize access to your accounts.

​
Step 2 - Create method to use MCP Server with LlamaIndex

This method handles multiple rounds of tool calls until a final response is ready, allowing the AI to chain tool executions for complex tasks. 
import json
from llama_index.core.agent.workflow import FunctionAgent, AgentWorkflow

async def llamaindex_with_mcp_server(mcp_server_url: str, user_query: str):
    llm = OpenAI(model="gpt-4o-mini", api_key=os.getenv("OPENAI_API_KEY"))

    all_tools = await aget_tools_from_mcp_url(
        mcp_server_url,
        client=BasicMCPClient(mcp_server_url)
    )

    communication_agent = FunctionAgent(
        name="communication_agent",
        description="Agent that can read emails from Gmail and send messages to Slack",
        tools=all_tools,
        llm=llm,
        system_prompt="You are a helpful assistant. Use the available tools to answer the user's question.",
        max_iterations=10
    )

    workflow = AgentWorkflow(
        agents=[communication_agent],
        root_agent="communication_agent"
    )

    resp = await workflow.run(user_msg=user_query)

    return resp.response.content

​
Step 3 - Run!

result = await llamaindex_with_mcp_server(
    mcp_server_url=response.strata_server_url, 
    user_query="Check my latest 5 emails and summarize them in a Slack message to #general"
)

print(f"\nFinal Response: {result}")
Perfect! You’ve integrated LLamaIndex with Strata MCP servers.

​
Next Steps

Integrations

Explore available MCP servers

API Reference

REST endpoints and schemas

​
Useful Resources

Happy building with LlamaIndex and Klavis! 🚀