How to Use the Zinrelo MCP in AutoGen

Q: Is it possible to check membership status with Zinrelo and AutoGen?

Absolutely. An agent can initiate the process by calling getmemberdetails. The resulting data becomes part of the debate, helping all agents converge on whether a new member needs to be enrolled using enrollmember.

Get consensus on loyalty decisions using AutoGen and Zinrelo MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zinrelo MCP to AutoGen

Create your Vinkius account to connect Zinrelo 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 Zinrelo with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Decision Making

AutoGen excels when the answer isn't obvious. You can set up agents to debate a customer service issue. One agent might argue for immediate point awarding using `award_points_activity`, while another challenges it by checking current rules via `get_loyalty_settings`. The system forces deliberation between competing perspectives, leading to a consensus decision that you'll trust.

Collaborative Data Auditing

Build an auditing team. One agent fetches the member's current standing using `get_member_details`, and another checks their full history via `list_member_transactions`. They then debate if a manual adjustment (like calling `deduct_points`) is warranted. This structured negotiation process ensures all angles are considered before any action is taken.

Negotiating Program Changes

Want to change how rewards work? Use AutoGen. Agents can discuss the impact of changing rules, perhaps debating if a new coupon type requires calling `redeem_reward` or updating settings using `get_loyalty_settings`. The outcome is a consensus plan. This moves beyond simple tool execution; it's about structured problem-solving powered by multiple AI voices.

Setup guide

Set up Zinrelo 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 Zinrelo 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="Zinrelo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Zinrelo 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="Zinrelo_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Zinrelo 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 Zinrelo. 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 Zinrelo 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 Zinrelo MCP in AutoGen

You assign different roles to agents. One agent gathers data using `list_loyalty_members`, while another uses that list to check specific member eligibility against current settings via `get_loyalty_settings`.

Yes. You can assign a 'Finance Agent' responsible for transactions. This agent will call `deduct_points` only after other agents have agreed that the deduction is necessary.

Absolutely. An agent can initiate the process by calling `get_member_details`. The resulting data becomes part of the debate, helping all agents converge on whether a new member needs to be enrolled using `enroll_member`.

Yes. You can build scenarios where different agents are responsible for calling specific tools, such as one agent running `award_points_purchase` and another running `award_points_activity` based on separate inputs.

The server manages customer loyalty data, specifically handling points balances (integers), member status (strings), and transaction records which are complex structured objects.

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