Connectto Markdown2doc, Postgres, Gong MCP Servers
Create powerful AI workflows by connecting multiple MCP servers including Markdown2doc, Postgres, Gong for enhanced automation capabilities in Klavis AI.
Markdown2doc
Convert markdown text to different file formats (pdf, docx, doc, html), based on Pandoc
Available Tools:
- convert_markdown_to_file
Postgres
PostgreSQL is a powerful, open source object-relational database system
Available Tools:
- query
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
Quick Setup Guide
Follow these steps to connect LangChain 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 LangChain and configure authentication settings.
Test & Deploy
Verify your connections work correctly and start using your enhanced AI capabilities.
LangChain + KlavisAI Integration Snippets
import os
import asyncio
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType
from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI
# Initialize clients
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
llm = ChatOpenAI(model="gpt-4o-mini", api_key=os.getenv("OPENAI_API_KEY"))
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,
)
postgres_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.POSTGRES,
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,
)
mcp_client = MultiServerMCPClient({
"markdown2doc": {
"transport": "streamable_http",
"url": markdown2doc_mcp_instance.server_url
},
"postgres": {
"transport": "streamable_http",
"url": postgres_mcp_instance.server_url
},
"gong": {
"transport": "streamable_http",
"url": gong_mcp_instance.server_url
}
})
tools = asyncio.run(mcp_client.get_tools())
agent = create_react_agent(
model=llm,
tools=tools,
)
response = asyncio.run(agent.ainvoke({
"messages": [{"role": "user", "content": "Your query here"}]
}))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 LangChain applications with these MCP servers.
Start For Free