How to Use the ReferralCandy MCP in AutoGen

Q: How do I register ReferralCandy MCP Server tools with AutoGen agents?

Use mcpservertools with your Vinkius server URL to fetch the tool definitions. Pass this tools list to your AssistantAgent constructor so it can invoke tools like getcampaign during conversations.

Q: How do AutoGen agents handle ReferralCandy purchase registrations?

An agent can parse incoming sales logs and call registerpurchase. If another agent flags the purchase as a duplicate using listpurchases, they will negotiate a resolution before executing the tool.

Run multi-agent debate and consensus on ReferralCandy marketing tasks using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ReferralCandy MCP to AutoGen

Create your Vinkius account to connect ReferralCandy 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 ReferralCandy with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Coordinate ReferralCandy tasks across AutoGen agents

This MCP Server enables your AutoGen multi-agent system to coordinate complex marketing workflows using `list_campaigns` and `send_invite`. You can set up an acquisition agent that identifies top customers and a communications agent that sends the invites. Because AutoGen relies on agent conversations, one agent can inspect the output of `get_stats` while another checks `list_pending_rewards`. They debate whether to adjust campaign parameters before finalizing any changes.

Validate purchases using the ReferralCandy MCP Server

Use `register_purchase` and `list_purchases` to build a reliable fraud detection loop in AutoGen. A security agent can audit purchase logs while a marketing agent pushes to register new referrals, resolving conflicts through structured debate. Setting up this MCP Server requires registering the tools with your AssistantAgent using the mcp_server_tools helper. AutoGen handles the schema conversion behind the scenes, allowing your agents to interact with the API naturally.

Analyze advocate profiles through multi-agent consensus

Deploy agents to analyze advocate performance using `get_referrer` and `get_top_referrers`. One agent can analyze advocate profiles for high-value targets, while another checks `list_rewards` to ensure payouts are aligned with performance. This collaborative approach ensures that rewards are only processed after multiple agents agree on the advocate's eligibility. The conversation history acts as a natural audit log for every referral action.

Setup guide

Set up ReferralCandy 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 ReferralCandy 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="ReferralCandy_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use mcp_server_tools with your Vinkius server URL to fetch the tool definitions. Pass this tools list to your AssistantAgent constructor so it can invoke tools like get_campaign during conversations.

Yes, you can configure a critic agent to review the advocate's profile via get_referrer before the primary agent calls send_invite. The invite is only sent once both agents reach consensus.

An agent can parse incoming sales logs and call register_purchase. If another agent flags the purchase as a duplicate using list_purchases, they will negotiate a resolution before executing the tool.

Yes, the Vinkius hosted server supports Streamable HTTP transports, allowing your AutoGen agents to connect reliably from any environment without complex local setups.

Vinkius executes all tool calls inside a zero-trust V8 isolate sandbox. Advocate profiles and purchase logs are processed in-memory and never written to persistent disk, ensuring complete data isolation.

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