How to Use the Saysimple MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK setup handle Saysimple template variables?

Yes, the agent uses gettemplate to inspect required variables, then formats your payload as a JSON string. It passes this validated string to sendmessage to start the WhatsApp conversation.

Q: How does the OpenAI Agents SDK manage Saysimple chat routing?

The agent queries active threads using listchats and checks agent assignment rules. It then calls assignchat to route the conversation to the correct human agent.

Q: Can I filter which messaging channels are available to my agent?

Run listchannels to retrieve all active SMS and WhatsApp channel IDs. You can hardcode these IDs in your agent system prompt or let the agent dynamically select the correct channel per message.

Run production-ready OpenAI Agents SDK workflows that manage WhatsApp chats and dispatch automated messages via Saysimple.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Saysimple MCP to OpenAI Agents SDK

Create your Vinkius account to connect Saysimple to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Saysimple with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate WhatsApp dispatch with OpenAI Agents SDK

The `send_message` tool lets your agent dispatch template-based WhatsApp messages directly from your Python runtime. You pass the template data as a raw JSON string, which the agent formats on the fly before hitting the API. Because this MCP setup handles multi-agent handoffs, you can have a triage agent run `list_templates` to find the right template, then pass the payload to an execution agent. The execution agent validates the variables against your schema before running the dispatch.

Real-time triage with Saysimple MCP Server tools

The `list_chats` tool pulls active conversation threads directly into your agent context window. From there, your agent evaluates which threads require immediate human eyes based on customer sentiment or keyword triggers. Once the agent identifies a high-priority conversation, it invokes `assign_chat` to hand the thread off to a specific support representative. This setup keeps your team focused on complex cases while the agent handles basic triage.

Contact sync and webhook monitoring

The `create_contact` tool registers new phone numbers and user details in your central database the moment a customer reaches out. Your agent checks existing records with `get_contact` to prevent duplicate entries. To keep your MCP Server message pipelines running smoothly, the agent runs `list_webhooks` to verify that active delivery receipts are pointing to your ingestion endpoint. If a webhook drops, the agent flags it in your OpenAI dashboard traces.

Setup guide

Set up Saysimple 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 Saysimple tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip and initialize the Saysimple MCP Server using the Vinkius streamable HTTP parameters. Pass this server instance to your agent constructor to auto-discover all eleven messaging tools.

Yes, the agent uses `get_template` to inspect required variables, then formats your payload as a JSON string. It passes this validated string to `send_message` to start the WhatsApp conversation.

The agent queries active threads using `list_chats` and checks agent assignment rules. It then calls `assign_chat` to route the conversation to the correct human agent.

Run `list_channels` to retrieve all active SMS and WhatsApp channel IDs. You can hardcode these IDs in your agent system prompt or let the agent dynamically select the correct channel per message.

Vinkius runs the server in an ephemeral V8 Isolate sandbox, meaning no contact details or phone numbers are stored on disk. Your API keys are injected at runtime and never exposed to the LLM.

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