Create powerful AI workflows by connecting multiple MCP servers including Markdown2doc, Gong, Plai for enhanced automation capabilities in Klavis AI.
Convert markdown text to different file formats (pdf, docx, doc, html), based on Pandoc
Gong is a revenue intelligence platform that captures and analyzes all revenue-related interactions to help sales teams close more deals. It provides conversation analytics, deal insights, and sales performance tracking through call recordings and transcripts
Plai is an AI-powered advertising platform that simplifies creating, managing, and optimizing Facebook, Instagram, and LinkedIn ad campaigns. It provides tools for lead generation, campaign insights, and automated ad management to help businesses scale their digital marketing efforts effectively.
Follow these steps to connect Google Gemini to these MCP servers
Sign up for KlavisAI to access our MCP server management platform.
Add your desired MCP servers to Gemini and configure authentication settings.
Verify your connections work correctly and start using your enhanced AI capabilities.
import os
from google import genai
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat
# Initialize clients
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
client = genai.Client(api_key=os.getenv("GOOGLE_API_KEY"))
user_message = "Your query here"
markdown2doc_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.MARKDOWN2DOC,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
gong_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.GONG,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
plai_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.PLAI,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Get tools from all MCP servers
markdown2doc_tools = klavis_client.mcp_server.list_tools(
server_url=markdown2doc_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.GEMINI,
)
gong_tools = klavis_client.mcp_server.list_tools(
server_url=gong_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.GEMINI,
)
plai_tools = klavis_client.mcp_server.list_tools(
server_url=plai_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.GEMINI,
)
# Combine all tools
all_tools = []
all_tools.extend(markdown2doc_tools.tools)
all_tools.extend(gong_tools.tools)
all_tools.extend(plai_tools.tools)
response = client.models.generate_content(
model="gemini-2.5-flash",
contents=user_message,
config=genai.types.GenerateContentConfig(
tools=all_tools,
),
)
Everything you need to know about connecting to these MCP servers
Join developers who are already using KlavisAI to power their Google Gemini applications with these MCP servers.
Start For Free