How to Use the Genius Referrals MCP in LangChain

Q: How do I track referral performance with Genius Referrals and LangChain?

You build an agent that calls listtrackedreferrals for a specific campaign. Then, you can chain that with getadvocatedetails to enrich the referral data with information about who sent it.

Q: Can I build a custom advocate approval flow using Genius Referrals and LangChain?

Yes. Your LangChain agent can use getadvocatedetails to check an advocate's history against your own criteria. Based on the output, the agent can decide whether to approve them, flag them, or ask for more information.

Q: What's the best way to list all bonuses from Genius Referrals in a LangChain agent?

Just have your agent call the listawardedbonuses tool. You can then process the list to calculate totals, identify top earners, or check for payout anomalies, all within the same chain.

Build referral program agents that chain actions together and automate payouts with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Genius Referrals MCP to LangChain

Create your Vinkius account to connect Genius Referrals to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Genius Referrals with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Advocate Onboarding

This isn't just about adding users, it's about creating a pipeline. You can chain `register_advocate` directly to `get_campaign_details` so your agent instantly assigns new advocates to your primary campaign. Here's the thing: the output of one tool becomes the input for the next. This creates a simple, observable sequence for growing your program. You can trace every step of the onboarding process right in LangSmith, so you know exactly what your agent did.

Create Real-Time Payout Logic

Build a ReAct agent that responds to new conversions the moment they happen. The agent sees a new event from `log_referral_conversion`, then immediately calls `get_advocate_details` to check that advocate's history and status. Based on the rules you define, the agent decides what to do next. It can flag the payout for manual review or approve it by adding it to the queue with `list_payout_requests`. You get a fully auditable decision-making process for every single reward.

Dynamic Reporting with a LangChain Agent

Stop exporting CSVs. Build a reporting agent that pulls live data from your Genius Referrals account. It starts by calling `list_referral_campaigns` to get a list of everything you're running. Then, for each campaign, the agent executes `list_top_performers` and `list_tracked_referrals` to assemble a complete performance snapshot. This isn't a stale dashboard. It's a live report your agent generates on demand, giving you the ground truth in seconds.

Setup guide

Set up Genius Referrals 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 Genius Referrals 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({
    "genius-referrals-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 Genius Referrals 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 Genius Referrals. 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 Genius Referrals 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 Genius Referrals MCP in LangChain

You build an agent that calls `list_tracked_referrals` for a specific campaign. Then, you can chain that with `get_advocate_details` to enrich the referral data with information about who sent it.

Yes. Your LangChain agent can use `get_advocate_details` to check an advocate's history against your own criteria. Based on the output, the agent can decide whether to approve them, flag them, or ask for more information.

Just have your agent call the `list_awarded_bonuses` tool. You can then process the list to calculate totals, identify top earners, or check for payout anomalies, all within the same chain.

It's handled by the Vinkius platform. You get a single endpoint token that you provide to the MCP adapter in LangChain. You don't have to manage API keys or OAuth flows for Genius Referrals directly.

The server only touches the data needed for a specific tool call, like advocate profiles, campaign settings, and referral conversion events. Each call runs in an ephemeral, sandboxed environment on Vinkius, meaning your data isn't stored or logged after your chain completes its run.

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