How to Use the ReferralHero MCP in LangChain

Q: Can I trace ReferralHero tools in LangChain using LangSmith?

Yes, every tool call made by your LangChain agent, such as getleaderboard or addpoints, is fully traced in LangSmith. You will see the exact JSON inputs and outputs, making it easy to debug failed referral operations.

Q: How does LangChain handle errors when ReferralHero tools fail?

LangChain catches exceptions thrown by tools like updatesubscriber and feeds the error message back to the agent's context. The agent can then analyze the error, adjust its parameters, and try the tool call again.

Run multi-step marketing chains in LangChain that automatically update ReferralHero subscriber points and track conversions.

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 LangChain

Create your Vinkius account to connect ReferralHero 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 ReferralHero with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain ReferralHero actions with LangChain agents

Your LangChain agent can now instantly execute marketing workflows by chaining the outputs of your database queries directly into the `add_subscriber` tool. When a user signs up on your site, the agent catches the event, fetches their details, and registers them to your campaign without manual coding. If you want to build complex referral loops, you can feed the output of `list_subscribers` back into your chain. The agent evaluates who needs an update and triggers `update_subscriber` in the same execution run, giving you a fully autonomous referral pipeline.

Debug ReferralHero tool calls using LangSmith tracing

Stop guessing why a referral didn't register. When your agent calls `track_conversion` inside a complex LangChain chain, LangSmith captures the exact payload, latency, and response from this MCP Server. You can inspect the inputs sent to `add_points` or `delete_subscriber` directly in your trace dashboard. This visibility ensures you don't accidentally credit the wrong user when running complex multi-step reasoning chains.

Build multi-step reasoning loops for campaign management

Combine this MCP Server with 500+ LangChain integrations to build smart marketing agents. Your agent can read a CSV of new leads from your CRM, check existing campaigns using `list_lists`, and dynamically decide which ReferralHero campaign fits best. The agent uses the `get_rewards` tool to verify available incentives before calling `add_subscriber`. Because LangChain manages the state across these steps, the agent makes informed decisions based on live campaign data.

Setup guide

Set up ReferralHero 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 ReferralHero 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({
    "referralhero-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 ReferralHero 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 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 LangChain

You load the tools from the MCP Server using the LangChain adapter and pass them directly to your agent constructor. The agent then gets access to tools like `add_subscriber` and `track_conversion` to execute them during its reasoning loop.

Yes, every tool call made by your LangChain agent, such as `get_leaderboard` or `add_points`, is fully traced in LangSmith. You will see the exact JSON inputs and outputs, making it easy to debug failed referral operations.

LangChain catches exceptions thrown by tools like `update_subscriber` and feeds the error message back to the agent's context. The agent can then analyze the error, adjust its parameters, and try the tool call again.

Yes, you can build a chain where a database tool retrieves a user's purchase history and this MCP Server uses `track_conversion` to reward their referrer. This lets you connect your internal transactional data with your referral campaigns.

Your subscriber emails, names, and transaction IDs are processed inside an ephemeral V8 sandbox that destroys itself after execution. Vinkius secures your API keys and handles the authentication handshake, so your LangChain code never exposes sensitive 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