How to Use the Genius Referrals MCP in AutoGen

Q: How do I set up a fraud detection team for Genius Referrals using AutoGen agents?

You create multiple agents: one to monitor logreferralconversion, another to investigate using getadvocatedetails, and a third to make a decision. They collaborate in a group chat to analyze and act on suspicious referrals.

Q: Can multiple AutoGen agents collaborate on managing a Genius Referrals campaign?

Absolutely. You can have one agent track performance with listtrackedreferrals and another manage payouts with listpayoutrequests. They can discuss their findings and coordinate actions to manage the campaign.

Q: What's a good agent setup in AutoGen for monitoring Genius Referrals advocate payouts?

A good setup is a FinanceAgent that periodically calls listawardedbonuses and listpayoutrequests. If it detects an anomaly, it can initiate a conversation with a ReviewerAgent to investigate further.

Let AI agents debate, collaborate, and manage your referral program with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Genius Referrals MCP to AutoGen

Create your Vinkius account to connect Genius Referrals 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 Genius Referrals with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up a Multi-Agent Fraud Review

Create a team of agents to analyze suspicious activity. A "monitor" agent watches for anomalies using `log_referral_conversion`. When it finds one, it alerts a second "investigator" agent in the group chat. The investigator uses `get_advocate_details` and `list_tracked_referrals` to gather evidence. It then presents its findings to a "decider" agent, which makes the final call. You get to see the entire debate unfold.

Let Agents Debate Campaign Strategy

Task a "growth" agent with finding top performers by calling `list_top_performers`. At the same time, have a "finance" agent monitor costs by watching `list_awarded_bonuses`. These two agents can then debate the next campaign's bonus structure in a conversation. The growth agent argues for higher rewards to motivate advocates, while the finance agent presents the budget impact until they reach a data-backed consensus.

Build a Referral Ops Team with AutoGen

An "onboarding" agent can use `register_advocate` to sign up new partners automatically. A separate "support" agent can be tasked to pull an advocate's full history with `get_advocate_details` when a question comes in. These specialized agents work together, passing information and tasks back and forth. It’s like having a dedicated ops team that runs entirely on the Genius Referrals MCP server tools, and you get to define how they interact.

Setup guide

Set up Genius Referrals 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 Genius Referrals 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="Genius Referrals_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You create multiple agents: one to monitor `log_referral_conversion`, another to investigate using `get_advocate_details`, and a third to make a decision. They collaborate in a group chat to analyze and act on suspicious referrals.

Absolutely. You can have one agent track performance with `list_tracked_referrals` and another manage payouts with `list_payout_requests`. They can discuss their findings and coordinate actions to manage the campaign.

A good setup is a `FinanceAgent` that periodically calls `list_awarded_bonuses` and `list_payout_requests`. If it detects an anomaly, it can initiate a conversation with a `ReviewerAgent` to investigate further.

Agents share information by posting messages in the group chat. One agent can call `get_campaign_details`, post the results, and another agent can read that message to inform its next action. It's a conversational workflow.

The server processes data like advocate IDs, referral stats, and bonus amounts. In an AutoGen setup, this data is passed between your agents as text within their conversational context. It all happens within the secure, zero-trust Vinkius runtime, which isolates the entire process.

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