How to Use the Genius Referrals MCP in LlamaIndex

Q: Can I query advocate performance from Genius Referrals with a LlamaIndex agent?

Yes. Once you've indexed data from tools like listtrackedreferrals and listtopperformers, you can ask your agent natural language questions about advocate performance, and it will query the index for answers.

Q: What's the process for indexing campaign data from Genius Referrals in LlamaIndex?

First, use the listreferralcampaigns tool to get all your campaign IDs. Then, loop through them, calling getcampaigndetails for each one and passing the resulting data into your LlamaIndex index.

Turn your live Genius Referrals data into a queryable knowledge base with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Genius Referrals to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Advocate History

Use the MCP tools to build a searchable history of your advocates. Set up a process to periodically run `list_program_advocates` and `get_advocate_details`, then pipe the results directly into a LlamaIndex vector store. Now you can ask plain-English questions like, "who are my top 10 advocates from the last quarter?" LlamaIndex will query the indexed data to give you a grounded answer, not a guess.

Build a RAG System for Campaign Strategy

Don't just list your campaigns, understand what makes them work. You can index the output of `get_campaign_details` and `list_tracked_referrals` for every campaign you've ever run. Your RAG application can now answer complex questions like, "which campaigns had the highest conversion rate in Q2?" It works by synthesizing information from your entire indexed referral history to find patterns you'd otherwise miss.

Query Payouts with LlamaIndex

Create an audit log you can actually search. Your agent can index every event from `list_payout_requests` and `list_awarded_bonuses` as they happen. This lets you ask your RAG system questions like, "show me all payouts over $100 to advocates who signed up this month." LlamaIndex finds the answer by searching the data it indexed from the Genius Referrals API, giving you instant oversight.

Setup guide

Set up Genius Referrals 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 Genius Referrals 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 Genius Referrals tools.",
)
response = await agent.run("List recent Genius Referrals 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 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 LlamaIndex

You use the McpToolSpec to load the Genius Referrals tools. Then, you run tools like `list_program_advocates` and feed the output into a LlamaIndex data connector to build your vector index.

Yes. Once you've indexed data from tools like `list_tracked_referrals` and `list_top_performers`, you can ask your agent natural language questions about advocate performance, and it will query the index for answers.

First, use the `list_referral_campaigns` tool to get all your campaign IDs. Then, loop through them, calling `get_campaign_details` for each one and passing the resulting data into your LlamaIndex index.

LlamaIndex itself doesn't cache the API calls. Its purpose is to take the data you pull from the MCP server and load it into a persistent vector index that you control.

The server processes advocate profiles, campaign details, and referral event data. When you use LlamaIndex, you are explicitly pulling this data to store it in your own vector index. The MCP server itself doesn't persist any of it; it's just the transport.

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