How to integrate Onesignal rest api MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Onesignal rest api Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Onesignal rest api to CrewAI using the Composio tool router. By the end, you'll have a working Onesignal rest api agent that can send push notification to all active users, list all devices registered for my app, view details of last 10 notifications, delete a device by player id through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Onesignal rest api account through Composio's Onesignal rest api 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:
  • Get a Composio API key and configure your Onesignal rest api connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Onesignal rest api
  • Build a conversational loop where your agent can execute Onesignal rest api 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 Onesignal rest api MCP server, and what's possible with it?

The Onesignal rest api MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your OneSignal account. It provides structured and secure access to your messaging platform, so your agent can perform actions like sending push notifications, managing devices, viewing app details, and segmenting audiences automatically on your behalf.

  • Automated push notifications and messaging: Instantly have your agent create and send targeted push notifications to your users, keeping them engaged and informed.
  • Device management and updates: Let your agent add, update, or remove registered devices (players) to keep your audience data fresh and accurate.
  • App insights and metadata retrieval: Effortlessly fetch and review detailed app information, notification history, and device lists for better operational visibility.
  • Audience segmentation and targeting: Enable your agent to view and utilize user segments, making it easy to target the right audience for every message.
  • Notification analytics and history: Have your agent retrieve past notifications, track delivery, and analyze engagement trends for continuous improvement.

Supported Tools & Triggers

Tools
Create NotificationTool to create and send a onesignal push notification.
Delete DeviceTool to delete a device (player) from a onesignal app.
Update DeviceTool to update properties of an existing device.
View OneSignal AppTool to retrieve metadata for a single onesignal app.
View DeviceTool to retrieve details of a specific device (player).
View DevicesTool to retrieve a paginated list of devices (players) for a onesignal app.
View NotificationsTool to retrieve details of multiple notifications.
View SegmentsTool to view segments for a onesignal app.

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

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.

Install dependencies

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

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

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
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 Onesignal rest api MCP URL

Create a Composio Tool Router session for Onesignal rest api

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["onesignal_rest_api"],
)
url = session.mcp.url
What's happening:
  • You create a Onesignal rest api only session through Composio
  • Composio returns an MCP HTTP URL that exposes Onesignal rest api tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Onesignal rest api Assistant",
    goal="Help users interact with Onesignal rest api through natural language commands",
    backstory=(
        "You are an expert assistant with access to Onesignal rest api tools. "
        "You can perform various Onesignal rest api operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Onesignal rest api MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Onesignal rest api operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Onesignal rest api related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_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:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_onesignal_rest_api_agent.py

Complete Code

Here's the complete code to get you started with Onesignal rest api and CrewAI:

python
# file: crewai_onesignal_rest_api_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Onesignal rest api session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["onesignal_rest_api"],
    )
    url = session.mcp.url

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

    # Create Onesignal rest api assistant agent
    toolkit_agent = Agent(
        role="Onesignal rest api Assistant",
        goal="Help users interact with Onesignal rest api through natural language commands",
        backstory=(
            "You are an expert assistant with access to Onesignal rest api tools. "
            "You can perform various Onesignal rest api operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Onesignal rest api operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Onesignal rest api related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

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

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Onesignal rest api through Composio's Tool Router. The agent can perform Onesignal rest api 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

How to build Onesignal rest api MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Onesignal rest api MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Onesignal rest api MCP with Claude Agent SDK

Google ADK

Google ADK

Use Onesignal rest api MCP with Google ADK

LangChain

LangChain

Use Onesignal rest api MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Onesignal rest api MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Onesignal rest api MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Onesignal rest api MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Onesignal rest api MCP?

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

Can I use Tool Router MCP with CrewAI?

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 Onesignal rest api tools.

Can I manage the permissions and scopes for Onesignal rest api while using Tool Router?

Yes, absolutely. You can configure which Onesignal rest api 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 Onesignal rest api data and credentials are handled as safely as possible.

Used by agents from

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