Create powerful collaborative AI workflows by connecting multiple MCP servers including Mixpanel, QuickBooks, Tavily for enhanced multi-agent automation capabilities in Klavis AI.
Mixpanel is a powerful product analytics platform that helps teams understand user behavior, track events, analyze conversion funnels, measure retention, and make data-driven decisions with real-time insights and advanced segmentation capabilities
QuickBooks is a comprehensive accounting software solution that helps small and medium businesses manage their finances, track expenses, create invoices, manage payroll, and generate financial reports with integrated banking and tax preparation features
Tavily is an AI-powered search API designed for LLMs and AI agents. Get real-time web search results, extract content from URLs, crawl websites, and generate site maps with advanced filtering and parsing capabilities
Follow these steps to connect CrewAI to these MCP servers
Sign up for KlavisAI to access our MCP server management platform.
Set up your CrewAI agents with your desired MCP servers tools and configure authentication settings for collaborative workflows.
Test your multi-agent workflows and start using your enhanced collaborative AI capabilities.
import os
from crewai import Agent, Task, Crew, Process
from crewai_tools import MCPServerAdapter
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType
# Initialize clients
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
mixpanel_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.MIXPANEL,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
quickbooks_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.QUICKBOOKS,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
tavily_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.TAVILY,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Initialize MCP tools for each server
mixpanel_tools = MCPServerAdapter(mixpanel_mcp_instance.server_params)
quickbooks_tools = MCPServerAdapter(quickbooks_mcp_instance.server_params)
tavily_tools = MCPServerAdapter(tavily_mcp_instance.server_params)
# Create specialized agents for each service
mixpanel_agent = Agent(
role="Mixpanel Specialist",
goal="Handle all Mixpanel related tasks and data processing",
backstory="You are an expert in Mixpanel operations and data analysis",
tools=mixpanel_tools,
reasoning=True,
verbose=False
)
quickbooks_agent = Agent(
role="QuickBooks Specialist",
goal="Handle all QuickBooks related tasks and data processing",
backstory="You are an expert in QuickBooks operations and data analysis",
tools=quickbooks_tools,
reasoning=True,
verbose=False
)
tavily_agent = Agent(
role="Tavily Specialist",
goal="Handle all Tavily related tasks and data processing",
backstory="You are an expert in Tavily operations and data analysis",
tools=tavily_tools,
reasoning=True,
verbose=False
)
# Define collaborative tasks
research_task = Task(
description="Gather comprehensive data from all available sources",
expected_output="Raw data and initial findings from all services",
agent=mixpanel_agent,
markdown=True
)
analysis_task = Task(
description="Analyze and synthesize the gathered data",
expected_output="Comprehensive analysis with insights and recommendations",
agent=quickbooks_agent,
markdown=True
)
# Create multi-agent crew
multi_agent_crew = Crew(
agents=[mixpanel_agent, quickbooks_agent, tavily_agent],
tasks=[research_task, analysis_task],
verbose=False,
process=Process.sequential
)
result = multi_agent_crew.kickoff()
Everything you need to know about connecting CrewAI to these MCP servers
Join developers who are already using KlavisAI to power their CrewAI multi-agent systems with these MCP servers.
Start For Free