Create powerful AI workflows by connecting multiple MCP servers including Google Docs, Resend, Firecrawl Web Search for enhanced automation capabilities in Klavis AI.
Google Docs is a word processor included as part of the free, web-based Google Docs Editors suite
Resend is a modern email API for sending and receiving emails programmatically
Advanced web crawling, scraping, and search capabilities powered by Firecrawl
Follow these steps to connect LangChain to these MCP servers
Sign up for KlavisAI to access our MCP server management platform.
Add your desired MCP servers to LangChain and configure authentication settings.
Verify your connections work correctly and start using your enhanced AI capabilities.
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"))
google_docs_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.GOOGLE_DOCS,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
resend_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.RESEND,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
firecrawl_web_search_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.FIRECRAWL_WEB_SEARCH,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
mcp_client = MultiServerMCPClient({
"google docs": {
"transport": "streamable_http",
"url": google_docs_mcp_instance.server_url
},
"resend": {
"transport": "streamable_http",
"url": resend_mcp_instance.server_url
},
"firecrawl web search": {
"transport": "streamable_http",
"url": firecrawl_web_search_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"}]
}))
Everything you need to know about connecting to these MCP servers
Join developers who are already using KlavisAI to power their LangChain applications with these MCP servers.
Start For Free