How to Use the ReferralCandy MCP in LlamaIndex

Q: Can LlamaIndex index historical ReferralCandy data for RAG?

Yes, you can run a script that calls listreferrals and loads the output into a vector index. This allows your LlamaIndex agent to answer semantic questions about your top advocates without making repeated API calls.

Q: How do I limit LlamaIndex agent access to ReferralCandy write tools?

You can use the allowedtools filter in the MCP client to exclude write tools like registerpurchase and sendinvite. This ensures your LlamaIndex agent only indexes read-only data.

Q: How does the agent retrieve specific campaign details?

The agent invokes getcampaign with the campaign ID. It then parses the metadata and uses it to answer user queries about active rewards or referral rules.

Index ReferralCandy advocate and campaign data into your LlamaIndex vector stores for grounded RAG.

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 LlamaIndex

Create your Vinkius account to connect ReferralCandy 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 ReferralCandy with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index ReferralCandy data into LlamaIndex vector stores

This MCP Server lets your LlamaIndex pipeline pull live advocate profiles and campaign structures using `get_referrer` and `list_campaigns`. Instead of querying raw tables, your agent indexes this data so you can search through advocate histories semantically. By feeding the output of `list_referrals` directly into your index, you build a searchable knowledge base of customer behavior. Your queries retrieve actual API data to ground your RAG applications, preventing hallucinations about who referred whom.

Query campaign performance with LlamaIndex MCP Server tools

Connect your LlamaIndex FunctionAgent to `get_stats` and `list_referrals_by_period` to perform complex analytics. Your agent queries the tools, builds a temporal view of your referrals, and indexes the results for quick retrieval. You set this up by wrapping the MCP client in McpToolSpec and converting it to a tool list. The agent uses these tools to pull fresh metrics, ensuring your marketing reports are always based on the latest data.

Track pending rewards and purchases in real time

Use `list_pending_rewards` and `register_purchase` to keep your LlamaIndex knowledge base completely current. Your agent can cross-reference physical purchases with pending rewards to flag discrepancies. The system supports filtering tools, meaning you can restrict your LlamaIndex agent to only access read-only tools like `list_rewards` when building public-facing dashboards. This keeps your write operations secure while maintaining searchability.

Setup guide

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

Install llama-index-tools-mcp and initialize the client. Wrap it in McpToolSpec and pass the async tool list to your FunctionAgent to start querying tools like get_campaign.

Yes, you can run a script that calls list_referrals and loads the output into a vector index. This allows your LlamaIndex agent to answer semantic questions about your top advocates without making repeated API calls.

You can use the allowed_tools filter in the MCP client to exclude write tools like register_purchase and send_invite. This ensures your LlamaIndex agent only indexes read-only data.

The agent invokes get_campaign with the campaign ID. It then parses the metadata and uses it to answer user queries about active rewards or referral rules.

Every request runs inside an ephemeral, zero-trust V8 sandbox on Vinkius. Your campaign structures and referral lists are fetched on demand and never cached, keeping your marketing data safe.

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