Vinkius
ReferralCandy logo
Vinkius
Vinkius runs on OpenAI Agents SDK

How to Use the ReferralCandy MCP in OpenAI Agents SDK

Run production-ready OpenAI Agents SDK setups that pull ReferralCandy metrics and trigger invites with built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

ReferralCandy MCP on Cursor AI Code Editor MCP Client ReferralCandy MCP on Claude Desktop App MCP Integration ReferralCandy MCP on OpenAI Agents SDK MCP Compatible ReferralCandy MCP on Visual Studio Code MCP Extension Client ReferralCandy MCP on GitHub Copilot AI Agent MCP Integration ReferralCandy MCP on Google Gemini AI MCP Integration ReferralCandy MCP on Lovable AI Development MCP Client ReferralCandy MCP on Mistral AI Agents MCP Compatible ReferralCandy MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on OpenAI Agents SDK

Connect ReferralCandy MCP to OpenAI Agents SDK

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

GDPR Included with Plan

Key Capabilities

Track advocate performance using OpenAI Agents SDK

The `get_top_referrers` tool identifies your most active brand advocates directly inside your agent workflows. Your agent can query this list, check individual profiles with `get_referrer`, and automatically tag high-value customers. It makes running VIP loyalty campaigns much easier because the agent handles the parsing. You don't have to write custom glue code to fetch these metrics. By feeding these MCP tools to your OpenAI Agents SDK, the model evaluates who deserves extra attention and forwards the data to your CRM.

Automate purchase registration and invites

The `register_purchase` tool logs new sales to attribute referrals correctly without manual database exports. When a customer buys something, your agent triggers this tool and immediately follows up by running `send_invite` to bring their friends on board. This keeps your referral loop tight. Instead of batching uploads at the end of the week, your agent handles transactions in real-time, keeping your ReferralCandy program data completely fresh.

Monitor campaign health and payouts via MCP Server

The `get_stats` tool exposes raw program performance metrics to your autonomous agent. It can cross-reference these numbers by running `list_pending_rewards` to make sure your marketing spend aligns with actual customer acquisition. If rewards start piling up, the agent flags the anomaly. You get instant visibility into pending payouts without having to log into a separate dashboard every morning.

Setup guide

Set up ReferralCandy MCP in OpenAI Agents SDK

Prerequisites

  • Python 3.10+ installed
  • openai-agents package (pip install openai-agents)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install the SDK

    Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.

  2. 2

    Connect via SSE transport

    Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all ReferralCandy tools at runtime.

  3. 3

    Create your Agent

    Pass the MCP to Agent(mcp_servers=[server]). The agent receives ReferralCandy tools as native definitions — JSON schemas resolve automatically.

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ReferralCandy tools and returns structured results. Copy the full example on the right to get started.

agent.py
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="ReferralCandy Agent",
            instructions="You have access to ReferralCandy tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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.

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 OpenAI Agents SDK

Install the SDK and point it to the Vinkius MCP endpoint using `MCPServerStreamableHttp`. The agent automatically discovers all 16 tools at runtime. You just need to pass the server configuration to your Agent constructor.
Yes, the agent can call `check_referralcandy_status` to confirm the API is responsive. This prevents your workflow from failing mid-execution during network blips. It is a clean way to handle pre-flight checks in production.
You can define strict input schemas and verification steps before the agent executes tools like `send_invite`. This prevents the model from accidentally spamming your customer list. The SDK validates every tool call against your rules.
You can set up a specialized triage agent that listens for purchases. When a sale occurs, it hands control to a referral agent equipped with `register_purchase` to log the event. This keeps your agent architectures modular and clean.
This MCP Server accesses advocate email addresses, purchase amounts, and referral codes to track campaign performance. Vinkius runs the server in an isolated V8 sandbox, meaning your keys and customer records never persist in memory.

Start using the ReferralCandy MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 16 tools

We've already built the connector for ReferralCandy. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 16 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.