Create powerful collaborative AI workflows by connecting multiple MCP servers including SendGrid, Fireflies for enhanced multi-agent automation capabilities in Klavis AI.
SendGrid is a cloud-based email delivery platform. Send transactional and marketing emails, manage contacts, track email analytics, handle bounces, and manage templates via OpenAPI integration
Fireflies.ai is an AI meeting assistant that automatically records, transcribes, and summarizes your meetings across Zoom, Google Meet, Teams, and other platforms. Extract action items, key insights, and searchable notes from all your conversations.
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"))
sendgrid_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.SENDGRID,
user_id="1234",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
fireflies_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.FIREFLIES,
user_id="1234",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Initialize MCP tools for each server
sendgrid_tools = MCPServerAdapter(sendgrid_mcp_instance.server_params)
fireflies_tools = MCPServerAdapter(fireflies_mcp_instance.server_params)
# Create specialized agents for each service
sendgrid_agent = Agent(
role="SendGrid Specialist",
goal="Handle all SendGrid related tasks and data processing",
backstory="You are an expert in SendGrid operations and data analysis",
tools=sendgrid_tools,
reasoning=True,
verbose=False
)
fireflies_agent = Agent(
role="Fireflies Specialist",
goal="Handle all Fireflies related tasks and data processing",
backstory="You are an expert in Fireflies operations and data analysis",
tools=fireflies_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=sendgrid_agent,
markdown=True
)
analysis_task = Task(
description="Analyze and synthesize the gathered data",
expected_output="Comprehensive analysis with insights and recommendations",
agent=fireflies_agent,
markdown=True
)
# Create multi-agent crew
multi_agent_crew = Crew(
agents=[sendgrid_agent, fireflies_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