How to integrate ReferralRock MCP with LlamaIndex

GET STARTED FOR FREE
Framework Integration Gradient
ReferralRock Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting ReferralRock to LlamaIndex using the Composio tool router. By the end, you'll have a working ReferralRock agent that can list all active referral campaigns, add a new member to referral program, show referral stats for this week through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a ReferralRock account through Composio's ReferralRock MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for ReferralRock
  • Connect LlamaIndex to the ReferralRock MCP server
  • Build a ReferralRock-powered agent using LlamaIndex
  • Interact with ReferralRock through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

What is the ReferralRock MCP server, and what's possible with it?

The ReferralRock MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your ReferralRock account. It provides structured and secure access so your agent can perform ReferralRock operations on your behalf.

Supported Tools & Triggers

Tools
Remove Email from Unsubscribe ListTool to remove an email address from the unsubscribe list.
Delete WebhookTool to delete a webhook subscription.
Delete Members from ProgramTool to delete members from a referral program.
Delete ReferralTool to delete one or more referrals from a referral program.
Delete RewardsTool to delete rewards from members or referrals in a referral program.
Get Email Unsubscribed StatusTool to check if an email address is unsubscribed from communications.
Get Webhook History for EventTool to retrieve webhook history for a specific event.
List Program MembersTool to list program members with filtering and pagination.
Get Member StatisticsTool to retrieve comprehensive statistics for a single member from ReferralRock.
Get PayoutTool to retrieve payout list by ID.
Get Payout Details by IDTool to get payout details by ID.
Get Pending PayoutsTool to get pending payouts for a member or recipient.
Get Payout TransactionsTool to get payout transaction history for referral program participants.
Get Single ProgramTool to retrieve a single referral program by name.
List Referral ProgramsList all referral programs in ReferralRock.
Get ReferralsTool to list referrals with filtering and pagination options.
Get Single ReferralTool to retrieve a single referral by email, ID, or external ID.
Get Reward RulesTool to get reward rules for a program.
Get RewardsTool to list rewards with optional filtering and pagination.
Remove Email from Unsubscribe ListTool to remove an email address from the unsubscribe list.
Unsubscribe Email AddressTool to unsubscribe an email address from the ReferralRock mailing list.
Create Webhook SubscriptionTool to create or update a webhook subscription for event notifications.
Create Invite Feed EntryTool to create an invite feed entry for automatic invitations.
Create Invite Feed EntriesTool to create multiple invite feed entries for automatic invites in ReferralRock.
Generate Member Access TokenTool to generate pre-authenticated member access URLs for sharing and portal experiences.
Generate Member Access URLsTool to generate member access URLs for custom share experience or secure portal embedding.
Add new member to programTool to create a new member and add them to a referral program.
Remove Members from ProgramTool to remove members from a referral program.
Create Referral ActionTool to create a referral action for processing recurring rewards.
Remove ReferralTool to remove referrals from a referral program.
Create New ReferralTool to create a new referral in ReferralRock based on a member's referral code.
Update Referral StatusTool to update referral status in ReferralRock.
Update Referral DetailsTool to update referral details in a referral program.
Issue Reward to MemberTool to issue a reward to a member in the Referral Rock system.
Remove RewardsTool to remove rewards from members or referrals of a referral program.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A ReferralRock account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and ReferralRock

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for ReferralRock access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called referralrock_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["referralrock"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform ReferralRock actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform ReferralRock actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, referralrock)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available ReferralRock tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your ReferralRock database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to ReferralRock

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with ReferralRock, then start asking questions.

Complete Code

Here's the complete code to get you started with ReferralRock and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["referralrock"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform ReferralRock actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform ReferralRock actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected ReferralRock to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes ReferralRock tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build ReferralRock MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use ReferralRock MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use ReferralRock MCP with Claude Agent SDK

Google ADK

Google ADK

Use ReferralRock MCP with Google ADK

LangChain

LangChain

Use ReferralRock MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use ReferralRock MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use ReferralRock MCP with Mastra AI

CrewAI

CrewAI

Use ReferralRock MCP with CrewAI

Claude Code

Claude Code

Use ReferralRock MCP with Claude Code

Codex

Codex

Use ReferralRock MCP with Codex

FAQ

What are the differences in Tool Router MCP and ReferralRock MCP?

With a standalone ReferralRock MCP server, the agents and LLMs can only access a fixed set of ReferralRock tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from ReferralRock and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right ReferralRock tools.

Can I manage the permissions and scopes for ReferralRock while using Tool Router?

Yes, absolutely. You can configure which ReferralRock scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your ReferralRock data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free