Seamlessly integrate your CrewAI multi-agent systems with LinkedIn using Klavis AI's comprehensive MCP server connection guide.
LinkedIn is a business and employment-oriented online service
Follow these steps to connect CrewAI to this MCP server
Sign up for KlavisAI to access our MCP server management platform.
Set up your CrewAI agents with the MCP server 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"))
linkedin_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.LINKEDIN,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
with MCPServerAdapter(linkedin_mcp_instance.server_params) as mcp_tools:
# Create a LinkedIn Analysis Agent
linkedin_agent = Agent(
role="LinkedIn Analyst",
goal="Research and analyze linkedin to extract comprehensive insights",
backstory="You are an expert at analyzing linkedin and creating professional summaries.",
tools=mcp_tools,
reasoning=True,
verbose=False
)
# Define Task
analysis_task = Task(
description=f"Research and analyze linkedin data. Extract relevant information and create a comprehensive summary with key points and main takeaways.",
expected_output="Complete analysis with structured summary, key insights, and main takeaways",
agent=linkedin_agent,
markdown=True
)
# Create and execute the crew
linkedin_crew = Crew(
agents=[linkedin_agent],
tasks=[analysis_task],
verbose=False,
process=Process.sequential
)
result = linkedin_crew.kickoff()
Everything you need to know about connecting CrewAI to this MCP server
Join developers who are already using KlavisAI to power their CrewAI multi-agent systems with this MCP server.
Start For Free