Connectto YouTube, Gong, Firecrawl Deep Research MCP Servers
Create powerful AI workflows by connecting multiple MCP servers including YouTube, Gong, Firecrawl Deep Research for enhanced automation capabilities in Klavis AI.
YouTube
Extract and convert YouTube video information to markdown format
Available Tools:
- get_youtube_video_transcript
Gong
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
Available Tools:
- gong_get_transcripts_by_user
- gong_get_extensive_data
- gong_get_call_transcripts
- +2 more tools
Firecrawl Deep Research
A personal research assistant that analyze sources across the web, based on Firecrawl
Available Tools:
- firecrawl_deep_research
Quick Setup Guide
Follow these steps to connect Google Gemini to these MCP servers
Create Your Account
Sign up for KlavisAI to access our MCP server management platform.
Configure Connections
Add your desired MCP servers to Gemini and configure authentication settings.
Test & Deploy
Verify your connections work correctly and start using your enhanced AI capabilities.
Google Gemini + KlavisAI Integration Snippets
import os
import google.generativeai as genai
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat
# Initialize clients
genai.configure(api_key=os.getenv("GOOGLE_AI_API_KEY"))
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
# Constants
GEMINI_MODEL = "gemini-2.5-flash"
user_message = "Your query 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,
)
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,
)
firecrawl_deep_research_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.FIRECRAWL_DEEP_RESEARCH,
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.GEMINI,
)
gong_tools = klavis_client.mcp_server.list_tools(
server_url=gong_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.GEMINI,
)
firecrawl_deep_research_tools = klavis_client.mcp_server.list_tools(
server_url=firecrawl_deep_research_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.GEMINI,
)
# Combine all tools
all_tools = []
all_tools.extend(youtube_tools.tools)
all_tools.extend(gong_tools.tools)
all_tools.extend(firecrawl_deep_research_tools.tools)
model = genai.GenerativeModel(
model_name=GEMINI_MODEL,
tools=all_tools
)
chat = model.start_chat()
response = chat.send_message(user_message)Frequently Asked Questions
Everything you need to know about connecting to these MCP servers
Ready to Get Started?
Join developers who are already using KlavisAI to power their Google Gemini applications with these MCP servers.
Start For Free