Create powerful AI workflows by connecting multiple MCP servers including Cal.com, GitLab for enhanced automation capabilities in Klavis AI.
Cal.com is an open-source scheduling platform that helps you schedule meetings without the back-and-forth emails. Manage event types, bookings, availability, and integrate with calendars for seamless appointment scheduling
GitLab is a comprehensive DevOps platform that provides Git repository management, CI/CD pipelines, issue tracking, and project management. Manage repositories, branches, merge requests, issues, pipelines, and collaborate with your development team
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"))
cal.com_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.CAL.COM,
user_id="1234",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
gitlab_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.GITLAB,
user_id="1234",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Get all MCP tools
cal.com_tools = klavis_client.mcp_server.list_tools(
server_url=cal.com_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
gitlab_tools = klavis_client.mcp_server.list_tools(
server_url=gitlab_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
# Combine all tools
all_tools = []
all_tools.extend(cal.com_tools.tools)
all_tools.extend(gitlab_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