How to Use the Wati MCP in AutoGen

Q: How does Wati's MCP Server interact with AutoGen?

You pass the list of tools—like listcontacts or sendmediamessage—to your AssistantAgent. The agents then use their conversational logic to decide which tool and what parameters to use.

Q: What data types are exposed by Wati's MCP Server for AutoGen?

The server exposes messaging content from listmessages, contact attributes from getcontact, and the structure of templates via listtemplates.

Debate messaging strategy with AutoGen and Wati's MCP Server.

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 AutoGen

Create your Vinkius account to connect Wati 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 Wati with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulate Messaging Strategy Debates

You can set up multiple agents—say, a 'Compliance Agent' and a 'Messaging Agent.' The Compliance Agent runs `check_wati_status` first to flag any connection risks. Then, the Messaging Agent uses that output to decide whether it can safely call `send_template_message`. The debate process converges on a single action: send or don't send. This is useful for complex decisions where risk assessment must precede execution.

Negotiate Contact Management Decisions

Need to update a user? Have one agent try to call `get_contact` to gather data, and let another challenge that data by cross-referencing it with the list of tags using `list_tags`. The agents debate which attributes are most critical before running `update_contact`. The system builds consensus on contact hygiene. This is better than a simple linear script because multiple perspectives validate the required change.

Determine Optimal Message Content

One agent might suggest sending a broadcast using `list_broadcasts`, while another challenges that by calling `get_contact` to confirm if individual users are actually subscribed. They debate whether a mass send is appropriate. The outcome of the conversation dictates the next tool call, which could be targeted communication via `send_session_message` instead of a broadcast.

Setup guide

Set up Wati 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 Wati 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="Wati_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Wati 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="Wati_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Wati 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 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 AutoGen

You pass the list of tools—like `list_contacts` or `send_media_message`—to your AssistantAgent. The agents then use their conversational logic to decide which tool and what parameters to use.

Absolutely. You can build scenarios where one agent gathers history using `list_messages`, passes that context, and a second agent uses it to formulate the content for `send_template_message`.

If an initial tool call fails (e.g., insufficient permissions), one of your agents can be tasked with analyzing the error output and proposing a fix, leading to a retry or alternative action.

The server exposes messaging content from `list_messages`, contact attributes from `get_contact`, and the structure of templates via `list_templates`.

Since agents debate over communication strategies, they handle sensitive contact attributes. You need to ensure that all discussions and resulting actions respect user PII guidelines.

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