Create powerful AI workflows by connecting multiple MCP servers including Asana, Cloudflare, WhatsApp for enhanced automation capabilities in Klavis AI.
Asana is a web and mobile application designed to help teams organize, track, and manage their work. It provides project management tools, task assignment, collaboration features, and progress tracking to boost team productivity
Cloudflare provides content delivery network services, DDoS protection, and security.
WhatsApp Business API integration that enables sending text messages, media, and managing conversations with customers. Perfect for customer support, marketing campaigns, and automated messaging workflows through the official WhatsApp Business platform.
Follow these steps to connect Together AI to these MCP servers
Sign up for KlavisAI to access our MCP server management platform.
Add your desired MCP servers to Together AI and configure authentication settings.
Verify your connections work correctly and start using your enhanced AI capabilities.
import os
import json
from together import Together
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat
# Initialize clients
together_client = Together(api_key=os.getenv("TOGETHER_API_KEY"))
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
asana_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.ASANA,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
cloudflare_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.CLOUDFLARE,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
whatsapp_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.WHATSAPP,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Get all MCP tools
asana_tools = klavis_client.mcp_server.list_tools(
server_url=asana_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
cloudflare_tools = klavis_client.mcp_server.list_tools(
server_url=cloudflare_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
whatsapp_tools = klavis_client.mcp_server.list_tools(
server_url=whatsapp_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
# Combine all tools
all_tools = []
all_tools.extend(asana_tools.tools)
all_tools.extend(cloudflare_tools.tools)
all_tools.extend(whatsapp_tools.tools)
messages = [
{"role": "system", "content": "You are a helpful AI assistant with access to multiple data sources."},
{"role": "user", "content": user_message}
]
response = together_client.chat.completions.create(
model="meta-llama/Llama-2-70b-chat-hf",
messages=messages,
tools=all_tools
)
Everything you need to know about connecting to these MCP servers
Join developers who are already using KlavisAI to power their Together AI applications with these MCP servers.
Start For Free