How to Use the Mav MCP in OpenAI Agents SDK

Get Mav running in OpenAI Agents SDK to automate your SMS lead qualification playbooks without manual oversight.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mav MCP to OpenAI Agents SDK

Create your Vinkius account to connect Mav 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 Mav with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automatic tool discovery for OpenAI Agents SDK

Your agent inspects the Mav MCP server upon startup to identify available playbooks. It maps your SMS logic directly into the execution flow without custom glue code. This setup keeps your production agent system clean. By enabling cacheToolsList, you minimize network overhead during high-frequency lead qualification tasks.

Production safety with built-in guardrails

Every action your agent takes undergoes validation before it hits the SMS gateway. This prevents the bot from sending unauthorized messages or malformed lead data. Tracing happens inside the OpenAI dashboard. You see exactly what your agent decided to do and why it chose that specific Mav playbook.

Reliable handoffs between specialized agents

You can delegate complex lead routing to secondary agents within the OpenAI environment. Mav acts as the primary interface for your SMS communication layer. This structure ensures your primary agent stays focused on high-level strategy. It triggers the Mav server only when it needs to initiate a customer conversation.

Setup guide

Set up Mav 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 Mav tools at runtime.
3

Create your Agent

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

Run the agent

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

Use the MCPServerStreamableHttp class within an async context manager. Pass the server instance to your Agent constructor to let the SDK handle auto-discovery.

Yes. Set cacheToolsList to true during initialization to speed up your agent response times. This is standard practice for production deployments.

It does. All tool calls route through the standard dashboard, giving you visibility into every SMS message sent by your agent.

The SDK catches exceptions during tool execution. Ensure your agent logic includes fallback paths if a specific playbook fails to trigger.

Mav treats your SMS lead records as ephemeral data. The connection between your agent and the server uses encrypted transport, ensuring no sensitive contact info persists in the middle layer.

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