Connectto Perplexity, Klavis ReportGen, Affinity MCP Servers

Create powerful AI workflows by connecting multiple MCP servers including Perplexity, Klavis ReportGen, Affinity for enhanced automation capabilities in Klavis AI.

Perplexity icon

Perplexity

coming soon

Perplexity is an AI research assistant that provides accurate answers and cites sources

Klavis ReportGen icon

Klavis ReportGen

featured

Generate visually appealing JavaScript web reports from search queries with Klavis AI.

Available Tools:

  • generate_web_reports
Affinity icon

Affinity

coming soon

Affinity is a relationship intelligence platform that helps teams manage relationships, track deals, and leverage network insights to drive business growth with powerful CRM and relationship mapping capabilities

Quick Setup Guide

Follow these steps to connect LangChain to these MCP servers

1

Create Your Account

Sign up for KlavisAI to access our MCP server management platform.

2

Configure Connections

Add your desired MCP servers to LangChain and configure authentication settings.

3

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"))

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,
)

klavis_reportgen_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.KLAVIS_REPORTGEN,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

affinity_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.AFFINITY,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

mcp_client = MultiServerMCPClient({
    "perplexity": {
        "transport": "streamable_http",
        "url": perplexity_mcp_instance.server_url
    },
    "klavis reportgen": {
        "transport": "streamable_http",
        "url": klavis_reportgen_mcp_instance.server_url
    },
    "affinity": {
        "transport": "streamable_http",
        "url": affinity_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