How to Use the 360dialog MCP in AutoGen

Q: How do I give 360dialog tools to my AutoGen agents?

You use the mcpservertools function from the autogen-ext library. It connects to the server endpoint and provides a list of tool functions that you pass to your AssistantAgent or UserProxyAgent during initialization.

Q: How can AutoGen agents decide which 360dialog template to use?

A 'Content' agent could use listtemplates and, based on its instructions, propose the best template name. A 'QA' agent could then review that proposal before the 'Sender' agent finally calls sendtemplatemessage. It's decision-making through conversation.

Deploy AutoGen agent teams that debate and decide how to use the 360dialog API for sending messages and managing WhatsApp campaigns.

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 AutoGen

Create your Vinkius account to connect 360dialog to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agents That Collaborate on Messaging

This server provides the tools for your AutoGen agents to control a 360dialog WhatsApp account. One agent can propose sending a message with `send_message`, while another checks if a pre-approved format exists using `list_templates`. This is where AutoGen shines. A 'CampaignManager' agent might suggest a mass message, but a 'Compliance' agent can use `get_template` to check the message against approved wording before giving the final OK to use `send_template_message`. The action only happens after they agree.

Multi-Agent Media and System Ops

The toolset covers more than just text. One agent can be responsible for using `upload_media` to prepare images or documents. Another agent can then take that media ID and use `send_media_message` to distribute it to a list of contacts. You can even create an 'Operator' agent whose whole job is system health. It can periodically run `check_360dialog_status` to monitor the API connection. If it detects a problem, it can alert other agents to pause their messaging tasks until the connection is restored.

Build Consensus with this MCP Server

AutoGen is about conversations between specialized agents. This MCP Server gives them a shared vocabulary for discussing and executing actions on WhatsApp. The tools are the verbs in their conversation. Because the `McpToolAdapter` handles the tool integration, you can focus on designing your agents' roles and prompts. You define the 'what' and 'why'—the MCP tools give your agent team the 'how' for interacting with the 360dialog API.

Setup guide

Set up 360dialog MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes 360dialog tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="360dialog_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent 360dialog data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="360dialog_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent 360dialog data")
    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 AutoGen

You use the `mcp_server_tools` function from the `autogen-ext` library. It connects to the server endpoint and provides a list of tool functions that you pass to your `AssistantAgent` or `UserProxyAgent` during initialization.

Yes, that's a perfect use case for AutoGen. You'd have a 'Validator' agent run `check_contacts` on a list of numbers. It would then pass the list of valid recipients to a 'Sender' agent, which would execute `send_message`.

A 'Content' agent could use `list_templates` and, based on its instructions, propose the best template name. A 'QA' agent could then review that proposal before the 'Sender' agent finally calls `send_template_message`. It's decision-making through conversation.

That's the core of AutoGen's conversational model. The agents will debate until they reach a consensus based on their initial prompts. An action like `send_message` will only be executed if the group chat concludes it's the right step.

No. The agent conversations happen entirely within your AutoGen environment. The MCP Server only sees the final, specific tool calls that an agent decides to execute, like a request to `send_message` with a phone number and text. Your agent's reasoning process remains private.

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