How to Use the 360dialog MCP in LangChain

Q: How do I use 360dialog tools within a LangChain agent?

You'll use the MultiServerMCPClient to get the tools, then pass them to an agent executor like createagent. LangChain handles mapping the agent's decisions to the correct 360dialog API call. It's designed to fit right into your existing chains.

Build LangChain agents that send WhatsApp messages, manage templates, and react to real-world events through the 360dialog API.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 360dialog MCP to LangChain

Create your Vinkius account to connect 360dialog 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 360dialog with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send and Manage Messages

This MCP Server gives your LangChain agent tools to interact with WhatsApp. You can `send_message` for plain text or `send_media_message` for images and files. It's not just about sending; your agent can also `list_templates` and `get_template` details to make sure it's using the right format. The real power in LangChain is chaining these actions. An agent could `check_contacts` to confirm a number, then `send_template_message` with a personalized greeting. LangSmith will trace every step, showing you exactly which tools were called and what the 360dialog API returned.

Automate Media and Webhooks

Your chains can handle media from start to finish. Use `upload_media` to get a file into the 360dialog system, then pass that ID directly to the `send_media_message` tool. You can also inspect existing media with `get_media`. For more complex workflows, the `set_webhook` tool is key. A LangChain agent can configure a callback URL on the fly, pointing 360dialog events to another service you control. This turns a simple messaging agent into a reactive system.

A Reliable 360dialog MCP Server

This isn't just a random collection of functions. These tools are built to work together inside your agent's reasoning loop. Your agent can use `check_360dialog_status` to confirm API connectivity before attempting a series of critical operations. Because this is a managed MCP Server, you don't worry about hosting or auth. You get a single endpoint and token. Your LangChain agent just focuses on the logic: when to send a message, which template to use, and how to respond to an incoming webhook.

Setup guide

Set up 360dialog 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 360dialog 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({
    "360dialog-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 360dialog 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 360dialog. 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 360dialog 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 360dialog MCP in LangChain

You'll use the `MultiServerMCPClient` to get the tools, then pass them to an agent executor like `create_agent`. LangChain handles mapping the agent's decisions to the correct 360dialog API call. It's designed to fit right into your existing chains.

Yes, that's what ReAct agents are for. You'd provide both the `send_message` and `send_template_message` tools to your agent. It will then decide which one to use based on the prompt and its internal reasoning steps.

The MCP adapter passes API errors back to the agent. You can build your chain to catch these exceptions and retry, or use a different tool. For example, if `send_message` fails, the agent could try `check_contacts` to see if the number is valid.

Absolutely. That's the main point. You can create a chain where the agent first queries a database for a customer's order status, then uses the 360dialog `send_template_message` tool to send them a WhatsApp update.

The server only processes data required by the specific tool your agent calls. This includes recipient phone numbers, message content, and media file URLs. All data is processed ephemerally and is encrypted in transit; we don't store your message history.

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