How to Use the ReferralCandy MCP in LangChain

Q: Can I use this server to distribute rewards?

You can use listpendingrewards to fetch outstanding payouts. Your agent can then process these rewards through your payment gateways and update the status accordingly.

Run multi-step ReferralCandy marketing workflows directly inside your LangChain chains and agents.

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 LangChain

Create your Vinkius account to connect ReferralCandy to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain ReferralCandy metrics to optimize advocacy campaigns

This MCP Server connects your LangChain agents directly to advocacy performance data using `get_stats` and `list_campaigns`. Your chain can grab live referral rates, evaluate which campaigns need a boost, and immediately decide the next logical routing step without hardcoded logic. You get full visibility into this decision loop using LangSmith tracing. If your agent calls `get_top_referrers` to find VIP advocates and then feeds that list into a personalized email chain, you can inspect every single tool input and output in real time.

Build autonomous loops with the ReferralCandy MCP Server

By feeding `list_pending_rewards` and `list_purchases` into your LangChain ReAct agents, you build self-correcting reward verification pipelines. The agent cross-references purchases with pending rewards, ensuring no advocate gets left behind or double-paid. Setting up this MCP Server takes just a few lines of code with the MultiServerMCPClient adapter. Once connected, your agent dynamically determines when to trigger `register_purchase` based on incoming webhook payloads in your chain.

Automate advocate invites based on chain logic

Use `send_invite` and `get_referrer` as standard LangChain tools to recruit new advocates automatically. Your agent checks if a customer is a good fit and triggers the invite sequence based on real-time customer behavior. Since LangChain supports over 500 integrations, you can easily combine these ReferralCandy tools with your existing SQL databases or vector stores. The agent retrieves user history from your database and instantly calls `list_invites` to avoid duplicate emails.

Setup guide

Set up ReferralCandy MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ReferralCandy tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "referralcandy-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ReferralCandy transactions"
    })
    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 LangChain

Install langchain-mcp-adapters and use MultiServerMCPClient pointing to the Vinkius URL. Pass the tools from client.get_tools() directly into your create_agent call to give your agent instant access to tools like list_campaigns.

Yes, your agent can run a chain that detects completed checkouts and calls register_purchase. You can monitor the latency and payload of this tool call inside LangSmith to ensure it runs correctly every time.

LangChain agents use ReAct loops to catch errors from tools like get_referrer. If a tool call fails, the agent reads the error output and tries a different approach, like verifying the advocate's email address first.

You can use list_pending_rewards to fetch outstanding payouts. Your agent can then process these rewards through your payment gateways and update the status accordingly.

Vinkius runs the server in an isolated V8 sandbox, meaning advocate profiles and purchase records are never stored on our servers. Your API keys are encrypted at rest, and all traffic flows through a single secure endpoint token.

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