How to Use the WSLA (WhatsApp) MCP in OpenAI Agents SDK

Q: How do I manage WhatsApp templates with WSLA (WhatsApp) and the OpenAI Agents SDK?

You start by calling listwhatsapptemplates to see all available message types. Then, you call sendwhatsapptemplate, passing in the required template name and parameters. The agent handles the rest of the API calls for you.

Q: Can WSLA (WhatsApp) send text messages using the OpenAI Agents SDK?

Yep, it can. Just use the sendwhatsapptext tool. This is your go-to method when you just need a quick, plain text message sent to a user's WhatsApp account.

Q: What if I want my agent to react to a message using WSLA (WhatsApp) and the OpenAI Agents SDK?

You call sendwhatsappreaction. This tool lets your AI client perform an action that mimics reacting to a message, keeping the conversation flow active without requiring complex text generation.

Q: Does this MCP Server support sending media details with WSLA (WhatsApp) and the OpenAI Agents SDK?

Absolutely. The getwhatsappmediadetails tool handles this. You feed it a piece of content ID, and your agent gets back all the necessary metadata about that media.

Automate WhatsApp messaging reliably with the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WSLA (WhatsApp) MCP to OpenAI Agents SDK

Create your Vinkius account to connect WSLA (WhatsApp) to OpenAI Agents SDK 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 WSLA (WhatsApp) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send and manage templates using the MCP Server.

You can list available message types first, checking which `list_whatsapp_templates` are active. After that, you send a specific template using `send_whatsapp_template`. This method ensures your messaging stays compliant with WhatsApp's rules.

Handle media and simple text actions.

Need to know what's in the picture? Run `get_whatsapp_media_details` on any given piece of content. For quick responses, your agent can use `send_whatsapp_text`. It’s fast, direct messaging that gets the job done.

Reacting to conversations with OpenAI Agents SDK.

Don't just send messages; acknowledge them. Your system executes a simple reaction using `send_whatsapp_reaction` when an event triggers it. This is useful for confirming receipt or showing quick support without needing full text generation.

Setup guide

Set up WSLA (WhatsApp) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all WSLA (WhatsApp) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives WSLA (WhatsApp) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate WSLA (WhatsApp) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="WSLA (WhatsApp) Agent",
            instructions="You have access to WSLA (WhatsApp) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 WSLA (WhatsApp). 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 WSLA (WhatsApp) 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 WSLA (WhatsApp) MCP in OpenAI Agents SDK

You start by calling `list_whatsapp_templates` to see all available message types. Then, you call `send_whatsapp_template`, passing in the required template name and parameters. The agent handles the rest of the API calls for you.

Yep, it can. Just use the `send_whatsapp_text` tool. This is your go-to method when you just need a quick, plain text message sent to a user's WhatsApp account.

You call `send_whatsapp_reaction`. This tool lets your AI client perform an action that mimics reacting to a message, keeping the conversation flow active without requiring complex text generation.

Absolutely. The `get_whatsapp_media_details` tool handles this. You feed it a piece of content ID, and your agent gets back all the necessary metadata about that media.

This server operates on WhatsApp message metadata and templates. Specifically, it handles text payloads and media identifiers, so you should always check your access scopes when building your agent workflows.

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