How to Use the ReferralHero MCP in AutoGen

Deploy AutoGen agents that debate and coordinate ReferralHero actions like subscriber updates and point allocations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ReferralHero MCP to AutoGen

Create your Vinkius account to connect ReferralHero to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ReferralHero with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run AutoGen multi-agent consensus for ReferralHero

Prevent automated mistakes by letting your AutoGen agents debate before executing tools. When a conversion event occurs, a validation agent can cross-reference the data before a second agent calls `track_conversion`. This collaborative approach ensures that actions like `add_points` are only triggered when all criteria are met. If the validation agent flags a suspicious transaction ID, the execution agent halts the process.

Automated subscriber cleanup with AutoGen debate loops

Maintain list hygiene without manual oversight. You can set up a conversation where one agent analyzes inactivity patterns from `list_subscribers` and proposes removing a user. A supervisor agent reviews the proposal against active campaigns found via `list_lists`. If they agree the subscriber is inactive, the execution agent calls `delete_subscriber` to clean up the campaign.

Run structured debates on ReferralHero reward distribution

Optimize your marketing spend by letting agents negotiate. One agent can query `get_rewards` to analyze current costs, while another reviews the current leaderboard using `get_leaderboard`. Together, they decide if a subscriber deserves a bonus and use `update_subscriber` to apply the changes. This MCP Server handles the actual API calls once the agents reach a consensus.

Setup guide

Set up ReferralHero 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 ReferralHero 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="ReferralHero_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the AutoGen MCP adapter to fetch the tools from your Vinkius MCP Server and pass them to your assistant agent. The agent can then use tools like `add_subscriber` and `update_subscriber` in its conversations.

Yes, you can set up a group chat where agents discuss whether to trigger `add_points`. The execution agent will only call the tool once the group reaches a consensus in the chat.

The AutoGen MCP adapter automatically translates the JSON schemas of tools like `get_subscriber` into the format AutoGen expects. This allows your agents to parse subscriber data without custom mapping code.

Yes, you can build cooperative workflows where one agent monitors campaigns using `list_lists` and another registers new participants via `add_subscriber`. The agents share state through their conversational history.

Your API keys and subscriber transaction logs are securely managed by Vinkius. The MCP Server runs inside an ephemeral, zero-trust sandbox, so your AutoGen agents only interact with clean tool interfaces without seeing credentials.

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