How to Use the ReferralHero MCP in LlamaIndex

Q: Can LlamaIndex query live ReferralHero leaderboards during a chat?

Yes, your LlamaIndex agent can run the getleaderboard tool in real time to fetch the latest rankings. The agent injects this live data directly into the LLM context window to answer user queries.

Index ReferralHero campaign data directly into LlamaIndex vector stores to query subscriber metrics with live RAG.

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 LlamaIndex

Create your Vinkius account to connect ReferralHero to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index ReferralHero subscriber lists using LlamaIndex

Stop writing SQL queries to find out who your top referrers are. This MCP Server lets your LlamaIndex agent fetch active users with `list_subscribers` and index their profiles directly into your vector store. Once indexed, you can run semantic queries to find patterns among your most active promoters. The agent combines live data from `get_leaderboard` with your indexed documents to give you real-time insights into campaign performance.

Build RAG pipelines grounded in ReferralHero campaign data

Feed live campaign structures into your query engine. By calling `get_list` and `get_rewards`, your LlamaIndex RAG application can answer user questions about current incentives with absolute accuracy. The agent retrieves the current rules directly from the API instead of relying on outdated training data. When a user asks what they get for referring a friend, the query engine pulls live data from this MCP Server to respond.

Query live referral transactions using LlamaIndex agents

Give your support agents a search tool that actually understands context. By wrapping `list_transactions` and `get_subscriber` in LlamaIndex tool specs, your agent can resolve referral disputes in seconds. When a customer asks why their points haven't updated, the agent queries the vector store, runs a live lookup via `get_subscriber`, and updates their balance using `add_points` if a discrepancy is found.

Setup guide

Set up ReferralHero MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all ReferralHero MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to ReferralHero tools.",
)
response = await agent.run("List recent ReferralHero data")

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 LlamaIndex

You use the LlamaIndex MCP tool spec to pull data from tools like `list_subscribers` and load the text chunks into a vector store index. This lets you perform semantic search on your active campaign participants.

Yes, your LlamaIndex agent can run the `get_leaderboard` tool in real time to fetch the latest rankings. The agent injects this live data directly into the LLM context window to answer user queries.

You install the MCP tool spec package, initialize the client with your Vinkius endpoint, and convert the tools to a list. Your LlamaIndex agent can then call tools like `add_subscriber` or `track_conversion` automatically.

Yes, you can build a decision-making agent that reads support documents and uses `add_points` to credit users. The agent evaluates the user's request against your indexed policies before initiating the tool call.

Your subscriber emails and transaction records are protected by Vinkius's zero-trust gateway. The MCP Server runs in an isolated V8 container, ensuring that sensitive referral data is never cached or leaked during indexing.

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