How to integrate Pushbullet MCP with OpenAI Agents SDK

This guide walks you through connecting Pushbullet to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Pushbullet agent that can send a note to your phone right now, list all devices linked to your account, share this pdf with your laptop through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Pushbullet account through Composio's Pushbullet MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Pushbullet logoPushbullet
Oauth2Api Key

Pushbullet is a notification and file sharing service for devices and browsers. It helps you instantly send messages, files, and links between your devices and contacts.

15 Tools

Introduction

This guide walks you through connecting Pushbullet to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Pushbullet agent that can send a note to your phone right now, list all devices linked to your account, share this pdf with your laptop through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Pushbullet account through Composio's Pushbullet MCP server.

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

Also integrate Pushbullet with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Pushbullet
  • Configure an AI agent that can use Pushbullet as a tool
  • Run a live chat session where you can ask the agent to perform Pushbullet operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Pushbullet MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Pushbullet account. It provides structured and secure access to your Pushbullet devices, chats, and pushes, so your agent can perform actions like sending notifications, sharing files, managing chats, and organizing devices on your behalf.

  • Instant push notifications and file sharing: Instruct your agent to send notes, links, or files to any connected device, user, or channel for seamless cross-device updates.
  • Device management and registration: Let your agent list, register, or remove devices from your Pushbullet account to keep your ecosystem up to date.
  • Chat creation and management: Have your agent create new chat threads, list ongoing conversations, or delete chats as needed for streamlined communication.
  • Bulk push and chat cleanup: Direct your agent to delete individual pushes, clear all pushes at once, or remove old chats and devices to keep your space organized.
  • User profile access and verification: Enable your agent to retrieve your current Pushbullet user profile, ensuring secure and accurate operations every time.

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Pushbullet project
  • Some knowledge of Python or Typescript
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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Pushbullet.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Pushbullet
const session = await composio.create(userId as string, {
  toolkits: ['pushbullet'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only pushbullet.
  • The router checks the user's Pushbullet connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Pushbullet.
  • This approach keeps things lightweight and lets the agent request Pushbullet tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Pushbullet. Help users perform Pushbullet operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Pushbullet and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Pushbullet operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Pushbullet.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Pushbullet and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['pushbullet'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Pushbullet. Help users perform Pushbullet operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Pushbullet MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Pushbullet.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Create Chat

Tool to create a new chat with the specified email address.

Register Device

Tool to register a new device under the current user's account.

Create Push

Tool to send a new push (note, link, or file) to a device, user, channel, or client.

Delete All Pushes

Tool to delete all pushes for the current user asynchronously.

Delete Chat

Tool to delete a chat by its identifier.

Delete Pushbullet Device

Tool to remove a device by its identifier.

Delete Push

Tool to delete a specific push by its identifier.

Get current user

Tool to retrieve the currently authenticated user's profile.

List Chats

Tool to list all chat objects for the current user.

List Devices

Tool to list all registered devices for the current user.

List Pushes

Tool to list pushes with optional filtering and pagination.

Mute or Unmute Chat

Tool to mute or unmute an existing chat.

Update Device

Tool to update metadata for a device by its identifier.

Update Push

Tool to update a push (dismiss or modify list items) by its identifier.

Upload Request

Tool to obtain a signed upload URL for a file before pushing.

FAQ

Frequently asked questions

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

Yes, you can. OpenAI Agents SDK 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 Pushbullet tools.

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

Start with Pushbullet.It takes 30 seconds.

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

Start building