Create powerful collaborative AI workflows by connecting multiple MCP servers including Plai, ServiceNow for enhanced multi-agent automation capabilities in Klavis AI.
Plai is an AI-powered advertising platform that simplifies creating, managing, and optimizing Facebook, Instagram, and LinkedIn ad campaigns. It provides tools for lead generation, campaign insights, and automated ad management to help businesses scale their digital marketing efforts effectively.
ServiceNow is a cloud-based software platform that helps companies manage and automate digital workflows for their enterprise operations, particularly in IT, human resources, and customer service.
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"))
plai_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.PLAI,
user_id="1234",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
servicenow_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.SERVICENOW,
user_id="1234",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Initialize MCP tools for each server
plai_tools = MCPServerAdapter(plai_mcp_instance.server_params)
servicenow_tools = MCPServerAdapter(servicenow_mcp_instance.server_params)
# Create specialized agents for each service
plai_agent = Agent(
role="Plai Specialist",
goal="Handle all Plai related tasks and data processing",
backstory="You are an expert in Plai operations and data analysis",
tools=plai_tools,
reasoning=True,
verbose=False
)
servicenow_agent = Agent(
role="ServiceNow Specialist",
goal="Handle all ServiceNow related tasks and data processing",
backstory="You are an expert in ServiceNow operations and data analysis",
tools=servicenow_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=plai_agent,
markdown=True
)
analysis_task = Task(
description="Analyze and synthesize the gathered data",
expected_output="Comprehensive analysis with insights and recommendations",
agent=servicenow_agent,
markdown=True
)
# Create multi-agent crew
multi_agent_crew = Crew(
agents=[plai_agent, servicenow_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