Create powerful AI workflows by connecting multiple MCP servers including Perplexity, Freshdesk, Google Jobs for enhanced automation capabilities in Klavis AI.
Perplexity is an AI research assistant that provides accurate answers and cites sources
Freshdesk is a cloud-based customer support software that helps businesses manage customer inquiries across multiple channels. Create and manage tickets, contacts, companies, and agents with powerful automation and collaboration features
Google Jobs is a comprehensive job search platform that aggregates listings from across the web. Search for jobs by location, company, employment type, and more, with detailed information about requirements, benefits, and application processes
Follow these steps to connect OpenAI to these MCP servers
Sign up for KlavisAI to access our MCP server management platform.
Add your desired MCP servers to OpenAI and configure authentication settings.
Verify your connections work correctly and start using your enhanced AI capabilities.
import json
import os
from openai import OpenAI
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat
# Initialize clients
openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
# Constants
OPENAI_MODEL = "gpt-4o-mini"
perplexity_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.PERPLEXITY,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
freshdesk_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.FRESHDESK,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
google_jobs_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.GOOGLE_JOBS,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Get tools from all MCP servers
perplexity_tools = klavis_client.mcp_server.list_tools(
server_url=perplexity_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
freshdesk_tools = klavis_client.mcp_server.list_tools(
server_url=freshdesk_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
google_jobs_tools = klavis_client.mcp_server.list_tools(
server_url=google_jobs_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
# Combine all tools
all_tools = []
all_tools.extend(perplexity_tools)
all_tools.extend(freshdesk_tools)
all_tools.extend(google_jobs_tools)
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": user_message}
]
response = openai_client.chat.completions.create(
model=OPENAI_MODEL,
messages=messages,
tools=all_tools if all_tools else None
)
Everything you need to know about connecting to these MCP servers
Join developers who are already using KlavisAI to power their OpenAI applications with these MCP servers.
Start For Free