Create powerful AI workflows by connecting multiple MCP servers including YouTube, ClickUp, Dropbox with Claude's advanced reasoning capabilities in Klavis AI.
Extract and convert YouTube video information to markdown format
ClickUp is a comprehensive project management and productivity platform that helps teams organize tasks, manage projects, and collaborate effectively with customizable workflows and powerful tracking features
Dropbox is a file hosting service that offers cloud storage and file synchronization
Follow these steps to connect Claude to these MCP servers
Sign up for KlavisAI to access our MCP server management platform and get your API keys.
Add your desired MCP servers to Claude and configure authentication settings with your Anthropic API key.
Verify your connections work correctly with Claude's function calling and start using your enhanced AI capabilities.
import os
import json
from anthropic import Anthropic
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat
# Initialize clients
anthropic_client = Anthropic(api_key=os.getenv("ANTHROPIC_API_KEY"))
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
# Constants
CLAUDE_MODEL = "claude-3-5-sonnet-20241022"
user_message = "Your message here"
youtube_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.YOUTUBE,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
clickup_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.CLICKUP,
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,
)
# Get tools from all MCP servers
youtube_tools = klavis_client.mcp_server.list_tools(
server_url=youtube_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
clickup_tools = klavis_client.mcp_server.list_tools(
server_url=clickup_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
dropbox_tools = klavis_client.mcp_server.list_tools(
server_url=dropbox_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
# Combine all tools
all_tools = []
all_tools.extend(youtube_tools.tools)
all_tools.extend(clickup_tools.tools)
all_tools.extend(dropbox_tools.tools)
messages = [
{"role": "user", "content": user_message}
]
response = anthropic_client.messages.create(
model=CLAUDE_MODEL,
max_tokens=4000,
messages=messages,
tools=all_tools
)
Everything you need to know about connecting Claude to these MCP servers
Join developers who are already using KlavisAI to power their Claude applications with these MCP servers.
Start For Free