How to Use the Leal MCP in OpenAI Agents SDK

Run autonomous loyalty campaigns in Latin America with your OpenAI Agents SDK system connected directly to Leal data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Leal MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Target high-value users with precision

The `list_segments` tool pulls customer groups directly into your OpenAI Agents SDK pipeline so your agent can trigger targeted retention campaigns. By feeding these segment lists directly to specialized agents, you avoid manual CSV exports and spreadsheet matching. Your agent uses `get_segment` to drill down into specific group criteria before executing a promotional run. This setup lets you pass structured segment data across different agents in your system, keeping every automated customer touchpoint highly relevant.

Verify customer balances before issuing rewards

The `get_member_balance` tool lets your agent check a customer's points total in real time before proposing any cashback or reward redemption. Running this check inside an OpenAI Agents SDK workflow ensures your system validates balances against actual ledger data before calling external APIs. You can configure built-in guardrails in your SDK setup to block agents from processing transactions if the points balance is insufficient. Tracing these balance checks through the OpenAI dashboard gives you a clear audit trail of every automated loyalty decision.

Audit loyalty transactions via this MCP Server

The `get_member_transactions` tool exposes a customer's entire loyalty history directly to your OpenAI Agents SDK system. Having this history on hand lets your agent detect weird spending patterns or confirm a recent purchase without human intervention. This MCP Server integration allows specialized customer support agents to pull transaction histories during chat sessions. When a customer disputes a point balance, the agent handles the entire lookup and resolution autonomously.

Setup guide

Set up Leal 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 Leal tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the Python package and pass the server URL to the streamable HTTP parameters. You then register the Leal server inside your agent constructor to let your system discover all 12 loyalty tools automatically.

Yes, because you can set up guardrails that intercept agent calls before they execute. Your agent checks points with `get_member_balance` and then runs a validation step to ensure the transaction complies with your business rules.

Use the OpenAI developer dashboard to trace every tool call and response payload. If `check_leal_status` returns an error, the dashboard shows the exact HTTP status code and latency metric to pinpoint the issue.

Turn on tool list caching in your configuration to avoid fetching the tool schemas on every single run. This reduces latency when your agent repeatedly calls `list_stores` to update location-based loyalty campaigns.

All customer data, including points balances and transaction histories retrieved by `get_member`, stays within your secure OpenAI runtime environment. Vinkius runs the server in an isolated sandbox, meaning your retail database credentials and customer records are never stored or exposed to external networks.

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