SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate ReferralRock MCP with CrewAI

Connect CrewAI to ReferralRock MCP. List all active referral campaigns, add a new member to referral program, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
ReferralRock logoReferralRock
Basic

ReferralRock is a referral marketing platform for creating and managing referral programs. It helps businesses drive word-of-mouth growth and increase customer acquisition.

32 Tools

Introduction

This guide walks you through connecting ReferralRock to CrewAI using the Composio tool router. By the end, you'll have a working ReferralRock agent that can add members to programs, create and update referrals, issue rewards, review payouts, and manage email unsubscribes through natural language commands.

This guide will help you understand how to give your CrewAI 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.

Also integrate ReferralRock with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexKimi CodeOpenClawHermesAtomic AgentCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your ReferralRock connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for ReferralRock
  • Build a conversational loop where your agent can execute ReferralRock operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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 to your referral programs, members, referrals, and rewards, so your agent can review programs, manage members, track referrals, generate member access links, and issue rewards on your behalf.

  • Referral program review: Have your agent list your referral programs and retrieve details about a specific program by name.
  • Member management: Let the agent list program members, add new members to a referral program, and review statistics for individual members.
  • Referral tracking and creation: Direct your agent to review referrals, find a specific referral, or create a new referral using a member's referral code.
  • Member access links: Instruct your agent to generate secure access links for custom sharing experiences or embedded member portals.
  • Reward management: Have your agent review available rewards and issue a reward to a program member.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step08 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A ReferralRock connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio crewai crewai-tools[mcp] python-dotenv
What's happening:
  • composio connects your agent to ReferralRock via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] includes MCP helpers
  • python-dotenv loads environment variables from .env
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model
5

Import dependencies

python
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

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

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")
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived ReferralRock MCP URL
6

Create a Composio Tool Router session for ReferralRock

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["referralrock"])

url = session.mcp.url
What's happening:
  • You create a ReferralRock only session through Composio
  • Composio returns an MCP HTTP URL that exposes ReferralRock tools
7

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.
8

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[agent], tasks=[task], verbose=False)
    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's Happening:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

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

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

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

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_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.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["referralrock"],
)
url = session.mcp.url

# Configure LLM
llm = LLM(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY"),
)

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

Conclusion

You now have a CrewAI agent connected to ReferralRock through Composio's Tool Router. The agent can perform ReferralRock operations through natural language commands.

Next steps:

  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations
TOOLS

Supported Tools

Every ReferralRock action and event your agent gets out of the box.

Remove Email from Unsubscribe List

Tool to remove an email address from the unsubscribe list.

Delete Webhook

Tool to delete a webhook subscription.

Delete Members from Program

Tool to delete members from a referral program.

Delete Referral

Tool to delete one or more referrals from a referral program.

Delete Rewards

Tool to delete rewards from members or referrals in a referral program.

Get Email Unsubscribed Status

Tool to check if an email address is unsubscribed from communications.

Get Webhook History for Event

Retrieve webhook history for a specific event using the deprecated raw-log history endpoint.

List Program Members

Tool to list program members with filtering and pagination.

Get Member Statistics

Tool to retrieve comprehensive statistics for a single member from ReferralRock.

Get Payout Details by ID

Retrieve a list of payouts using the supplied ID.

Get Pending Payouts

Tool to get pending payouts for a member or recipient.

Get Payout Transactions

Tool to get payout transaction history for referral program participants.

Get Single Program

Tool to retrieve a single referral program by name.

List Referral Programs

List all referral programs in ReferralRock.

Get Referrals

Tool to list referrals with filtering and pagination options.

Get Single Referral

Tool to retrieve a single referral by email, ID, or external ID.

Get Reward Rules

Tool to get reward rules for a program.

Get Rewards

Tool to list rewards with optional filtering and pagination.

Remove Email from Unsubscribe List

Tool to remove an email address from the unsubscribe list.

Unsubscribe Email Address

Tool to unsubscribe an email address from the ReferralRock mailing list.

Create Webhook Subscription

Tool to create or update a webhook subscription for event notifications.

Create Invite Feed Entry

Add a single contact for automatic invitations using the deprecated invite feed endpoint.

Create Invite Feed Entries

Tool to create multiple invite feed entries for automatic invites in ReferralRock.

Generate Member Access URLs

Generate a member's unique share and access links for a custom share experience or secure portal embedding, with optional expiration.

Add new member to program

Create a new member and add them to a referral program using their program ID, name, and email.

Remove Members from Program

Tool to remove members from a referral program.

Create Referral Action

Tool to create a referral action for processing recurring rewards.

Remove Referral

Remove referrals from a referral program using referral IDs or alternative identifiers.

Create New Referral

Tool to create a new referral in ReferralRock based on a member's referral code.

Update Referral Details

Tool to update referral details in a referral program.

Issue Reward to Member

Tool to issue a reward to a member in the Referral Rock system.

Remove Rewards

Tool to remove rewards from members or referrals of a referral program.

FRAMEWORKS

How to build ReferralRock MCP Agent with another framework

Claude Code logo

Claude Code

Use ReferralRock MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use ReferralRock MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use ReferralRock MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use ReferralRock MCP with Claude Agent SDK

Codex logo

Codex

Use ReferralRock MCP with Codex

Kimi Code logo

Kimi Code

Use ReferralRock MCP with Kimi Code

OpenClaw logo

OpenClaw

Use ReferralRock MCP with OpenClaw

Hermes logo

Hermes

Use ReferralRock MCP with Hermes

Atomic Agent logo

Atomic Agent

Use ReferralRock MCP with Atomic Agent

CLI logo

CLI

Use ReferralRock MCP with CLI

Google ADK logo

Google ADK

Use ReferralRock MCP with Google ADK

LangChain logo

LangChain

Use ReferralRock MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use ReferralRock MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use ReferralRock MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use ReferralRock MCP with LlamaIndex

Pydantic AI logo

Pydantic AI

Use ReferralRock MCP with Pydantic AI

AutoGen logo

AutoGen

Use ReferralRock MCP with AutoGen

FAQ

Frequently asked questions

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.

Yes, you can. CrewAI 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.

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.

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.

Start with ReferralRock.It takes 30 seconds.

Managed auth, hosted MCP servers, and every ReferralRock tool your agent needs.Free to start.

Start building