How to Use the 2Chat MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system use multiple 2Chat numbers?

Yes. The agent calls listnumbers to see all active lines connected to your account. From there, it dynamically selects the right fromnumber to pass into the message tool.

Deploy production OpenAI Agents SDK systems that safely send WhatsApp alerts and manage customer groups with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 2Chat MCP to OpenAI Agents SDK

Create your Vinkius account to connect 2Chat 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 2Chat with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate WhatsApp numbers inside OpenAI Agents SDK

Your autonomous agents need to verify contacts before blasting messages. This MCP Server lets your system call `check_number` to see if a phone number actually exists on WhatsApp, cutting down on failed delivery errors before they hit your API bill. Because the OpenAI Agents SDK handles guardrails natively, you can intercept the tool call. Your agent checks the status, and if it's invalid, the system automatically triggers a handoff to a human support agent instead of wasting retries.

Manage active WhatsApp groups dynamically

Keeping track of client chats shouldn't require manual database lookups. Your agents can query `list_groups` to find existing chats or spin up new ones instantly using `create_group` to onboard team members on the fly. The SDK traces these operations directly on your OpenAI dashboard. You see exactly when an agent created a group, which participants were added, and how the model decided to organize the conversation.

Send automated media and text alerts

Push updates to your users where they actually read them. By exposing `list_numbers` to your agent, it selects the correct outbound line and triggers `send_message` with either plain text or public media URLs. This setup avoids hardcoded routing rules. The agent evaluates the customer context, picks the best connected number, and fires off the receipt or PDF directly through the WhatsApp network.

Setup guide

Set up 2Chat 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 2Chat tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives 2Chat tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate 2Chat 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="2Chat Agent",
            instructions="You have access to 2Chat 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 2Chat. 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 2Chat 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 2Chat MCP in OpenAI Agents SDK

Install the SDK and use the MCPServerStreamableHttp class to point to your Vinkius MCP endpoint. Pass this server instance into your Agent constructor, and the model will auto-discover all five tools instantly.

Yes. The agent calls `list_numbers` to see all active lines connected to your account. From there, it dynamically selects the right from_number to pass into the message tool.

You can configure the SDK guardrails to monitor tool execution. If WhatsApp flags a rate limit, your agent can catch the error, pause, or switch to an alternative outbound number.

No. The MCP integration automatically translates the WhatsApp tool schemas into format-compliant definitions that your OpenAI models understand out of the box.

All transit payloads containing phone numbers and message content run inside isolated V8 sandboxes. Your sensitive credentials never touch public logs, ensuring your customer communications stay 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