How to Use the Wati MCP in LangChain

Q: How do I check Wati contacts using LangChain?

You use listwhatsappcontacts within your chain. This provides a list of all available numbers, which you can then pass to other tools or process further in subsequent steps.

Build complex conversational logic with LangChain's multi-step agentic workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wati MCP to LangChain

Create your Vinkius account to connect Wati 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 Wati with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send sequenced WhatsApp messages via MCP Server

You can initiate a message sequence using `get_whatsapp_contact_details` to pull profile info. Your LangChain agent then decides whether to use `send_template_message` or send a free-text session message, feeding the result into the next step of your chain. This allows you to build complex interactions where getting contact data directly determines the appropriate messaging method.

Analyze chat history with LangChain

Use `get_whatsapp_chat_history` when your agent needs context. The output of this tool—the message log for a given phone number—becomes the primary input for subsequent reasoning steps in your chain. You can then combine that history with `list_whatsapp_contacts` to determine if the contact is active or requires different follow-up logic.

Manage and audit campaigns using MCP Server

Before sending anything, check what's available. Call `list_whatsapp_templates` to see all approved messages your agent can use. You can then list previous activity with `list_broadcast_campaigns` to ensure the proposed campaign aligns with past efforts. This chain ensures that every action taken by your LangChain agent is validated against existing system resources.

Setup guide

Set up Wati 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 Wati 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({
    "wati-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 Wati 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 Wati. 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 Wati 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 Wati MCP in LangChain

The LangChain framework treats the MCP Server as a set of callable tools. You pass the tool definitions directly to your ReAct agent, allowing it to decide which functions like `send_session_message` to call and in what order.

Wati supports operational data: contact details, message history logs from `get_whatsapp_chat_history`, and structured campaign lists. All these outputs are treated as variable inputs for your agent's next step.

Yes. You can design a chain where the initial tool call (e.g., checking contact details) dictates whether the final action is sending an approved template or drafting a custom message.

You use `list_whatsapp_contacts` within your chain. This provides a list of all available numbers, which you can then pass to other tools or process further in subsequent steps.

The server handles operational data like contact phone numbers and message history. Since the MCP Server is stateless by default, you manage persistent context explicitly using `client.session()` to ensure security.

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