How to Use the Leal MCP in AutoGen

Debate loyalty strategy using AutoGen. Let agents negotiate reward offers and member segments for your retail business.

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 AutoGen

Create your Vinkius account to connect Leal to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate offers with AutoGen agents

Deploy a marketing agent and a finance agent to debate the best use of `list_rewards`. They compare reward costs against member balances to find the most effective promotion. This debate logic ensures your strategy isn't one-sided. One agent focuses on conversion while the other keeps an eye on the budget, using data from `get_member_balance` to inform their stance.

Multi-agent loyalty analysis with MCP Server

Have your agents challenge each other using `list_transactions`. One agent identifies a trend in purchase frequency, and the other verifies it against the raw record history. This consensus-based approach filters out bad data. The agents only act when they agree on the interpretation of the transaction records provided by the server.

Manage segments via AutoGen debate

Use `list_segments` to feed your agents a list of customer groups. They discuss which segment needs more attention, then use `get_segment` to drill into specific details. This creates a deliberate process for your marketing campaigns. The agents refine their target list before you ever send a single message to a customer.

Setup guide

Set up Leal MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Leal tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Leal_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Leal data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Leal_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Leal data")
    print(result.messages[-1].content)

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 AutoGen

You import the McpToolAdapter and pass the server tools to your AssistantAgent. The adapter handles the schema so your agents can talk to the API immediately.

Agents pass information back and forth during their debate. They can share member point totals or store locations to reach a group decision.

Everything stays within your secure Vinkius sandbox. Your agents only process the specific customer transaction data they need to complete the task.

No. You just point the adapter to the Vinkius URL. The agents automatically recognize the available tool definitions.

We enforce strict access controls on the endpoint. The agents only access the specific member transaction records you authorize them to retrieve.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.