How to Use the Kylas MCP in LangChain

Q: How do I connect the Kylas MCP Server to my LangChain agent?

Install the adapter package using pip install langchain-mcp-adapters langgraph to hook up the MCP client. Then, initialize the client using MultiServerMCPClient with the Vinkius HTTP endpoint and pass the tools to your agent creator.

Q: Can LangChain handle bulk lead listing from Kylas?

Yes, your agent calls listleads to pull multiple records in a single chain step. You can then pass this array directly to a vector store or use it to generate daily sales summaries.

Q: How does the Kylas tool execution show up in LangSmith when using LangChain?

Every call to getlead or listdeals is tracked as a distinct tool run in your LangSmith dashboard. You see the exact JSON inputs, outputs, and the latency of each CRM interaction.

Run multi-step sales pipelines in LangChain by linking your Indian SMB lead data directly to autonomous MCP chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kylas MCP to LangChain

Create your Vinkius account to connect Kylas to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kylas with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step sales chains in LangChain

The `get_lead` tool pulls raw customer data directly into your active execution chain. With this MCP Server, your LangChain agent fetches a lead using `get_lead` and immediately feeds that raw output into the next chain step to schedule follow-ups. You build actual reasoning loops where the agent looks at the lead's status and decides what action to trigger next.

Automate Indian SMB contact creation

The `create_contact` tool registers new prospects in your CRM database instantly. This integration lets your agent run `create_contact` the second a new prospect reaches out, keeping your database clean without manual data entry. You combine this with `list_contacts` to check if a prospect already exists before creating duplicates.

Track deal pipelines with real-time context

The `list_deals` tool exposes active pipeline opportunities to your reasoning loops. Your LangChain agent queries your active sales pipeline by calling `list_deals` to see which prospects are stalling. It reads the current pipeline state, matches it against pending actions, and flags high-priority items.

Setup guide

Set up Kylas MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kylas tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kylas-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kylas transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kylas. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kylas now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kylas MCP in LangChain

Install the adapter package using `pip install langchain-mcp-adapters langgraph` to hook up the MCP client. Then, initialize the client using `MultiServerMCPClient` with the Vinkius HTTP endpoint and pass the tools to your agent creator.

Yes, your agent calls `list_leads` to pull multiple records in a single chain step. You can then pass this array directly to a vector store or use it to generate daily sales summaries.

Every call to `get_lead` or `list_deals` is tracked as a distinct tool run in your LangSmith dashboard. You see the exact JSON inputs, outputs, and the latency of each CRM interaction.

You mix these MCP tools with over 500 existing integrations in the same reasoning chain. This lets your agent pull a record with `get_lead` and instantly write it to a database or send a message.

Vinkius runs this server inside an isolated, zero-trust sandbox where your lead names, contact details, and deal values are never stored. All credentials for the CRM API are handled securely on our servers, so your agent only sees the clean output of your queries.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript