Connectto Salesforce, Dropbox, Firecrawl Web Search MCP Servers

Create powerful collaborative AI workflows by connecting multiple MCP servers including Salesforce, Dropbox, Firecrawl Web Search for enhanced multi-agent automation capabilities in Klavis AI.

Salesforce icon

Salesforce

featured

Salesforce is the world's leading customer relationship management (CRM) platform that helps businesses connect with customers, partners, and potential customers

Available Tools:

  • salesforce_get_accounts
  • salesforce_create_account
  • salesforce_update_account
  • +24 more tools
Dropbox icon

Dropbox

coming soon

Dropbox is a file hosting service that offers cloud storage and file synchronization

Firecrawl Web Search icon

Firecrawl Web Search

featured

Advanced web crawling, scraping, and search capabilities powered by Firecrawl

Available Tools:

  • firecrawl_scrape
  • firecrawl_map
  • firecrawl_crawl
  • +6 more tools

Quick Setup Guide

Follow these steps to connect CrewAI to these MCP servers

1

Create Your Account

Sign up for KlavisAI to access our MCP server management platform.

2

Configure Agents & Tools

Set up your CrewAI agents with your desired MCP servers tools and configure authentication settings for collaborative workflows.

3

Deploy Your Crew

Test your multi-agent workflows and start using your enhanced collaborative AI capabilities.

CrewAI + KlavisAI Integration Snippets

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"))

salesforce_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.SALESFORCE,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

dropbox_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.DROPBOX,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

firecrawl_web_search_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.FIRECRAWL_WEB_SEARCH,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

# Initialize MCP tools for each server
salesforce_tools = MCPServerAdapter(salesforce_mcp_instance.server_params)
dropbox_tools = MCPServerAdapter(dropbox_mcp_instance.server_params)
firecrawl_web_search_tools = MCPServerAdapter(firecrawl_web_search_mcp_instance.server_params)

# Create specialized agents for each service
salesforce_agent = Agent(
    role="Salesforce Specialist",
    goal="Handle all Salesforce related tasks and data processing",
    backstory="You are an expert in Salesforce operations and data analysis",
    tools=salesforce_tools,
    reasoning=True,
    verbose=False
)

dropbox_agent = Agent(
    role="Dropbox Specialist",
    goal="Handle all Dropbox related tasks and data processing",
    backstory="You are an expert in Dropbox operations and data analysis",
    tools=dropbox_tools,
    reasoning=True,
    verbose=False
)

firecrawl_web_search_agent = Agent(
    role="Firecrawl Web Search Specialist",
    goal="Handle all Firecrawl Web Search related tasks and data processing",
    backstory="You are an expert in Firecrawl Web Search operations and data analysis",
    tools=firecrawl_web_search_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=salesforce_agent,
    markdown=True
)

analysis_task = Task(
    description="Analyze and synthesize the gathered data",
    expected_output="Comprehensive analysis with insights and recommendations",
    agent=dropbox_agent,
    markdown=True
)

# Create multi-agent crew
multi_agent_crew = Crew(
    agents=[salesforce_agent, dropbox_agent, firecrawl_web_search_agent],
    tasks=[research_task, analysis_task],
    verbose=False,
    process=Process.sequential
)

result = multi_agent_crew.kickoff()

Frequently Asked Questions

Everything you need to know about connecting CrewAI to these MCP servers

Ready to Get Started?

Join developers who are already using KlavisAI to power their CrewAI multi-agent systems with these MCP servers.

Start For Free