How to integrate Bannerbear MCP with OpenAI Agents SDK

This guide walks you through connecting Bannerbear to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Bannerbear agent that can merge multiple marketing pdfs into one file, list all video assets created this week, get available fonts for instagram templates through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Bannerbear account through Composio's Bannerbear MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Bannerbear logoBannerbear
Api Key

Bannerbear is an API-driven platform for generating images and videos automatically at scale. It helps businesses create custom graphics, social visuals, and marketing assets using powerful templates.

33 Tools

Introduction

This guide walks you through connecting Bannerbear to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Bannerbear agent that can merge multiple marketing pdfs into one file, list all video assets created this week, get available fonts for instagram templates through natural language commands.

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

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

Also integrate Bannerbear 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 Bannerbear
  • Configure an AI agent that can use Bannerbear as a tool
  • Run a live chat session where you can ask the agent to perform Bannerbear 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 Bannerbear MCP server, and what's possible with it?

The Bannerbear MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bannerbear account. It provides structured and secure access to your Bannerbear workspace, so your agent can generate images, create videos, manage templates, merge PDFs, and retrieve creative assets on your behalf.

  • Automated image and video generation: Enable your agent to create customized graphics or videos at scale using your Bannerbear templates and project assets.
  • Template browsing and management: Let your agent list, inspect, and select templates or template sets for creative projects, making it easy to automate content workflows.
  • Font and asset discovery: Have your agent retrieve available fonts and signed bases, ensuring the right design elements are used for every creative output.
  • PDF merging automation: Direct your agent to combine multiple PDFs into a single document, streamlining report or collateral creation.
  • Account and usage monitoring: Allow your agent to fetch current account status, API usage, and quota information to keep your creative operations running smoothly.

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 Bannerbear 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 Bannerbear.
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 Bannerbear
const session = await composio.create(userId as string, {
  toolkits: ['bannerbear'],
});
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 bannerbear.
  • The router checks the user's Bannerbear connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Bannerbear.
  • This approach keeps things lightweight and lets the agent request Bannerbear 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 Bannerbear. Help users perform Bannerbear 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 Bannerbear 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 Bannerbear 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 Bannerbear.
  • 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 Bannerbear 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: ['bannerbear'],
  });
  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 Bannerbear. Help users perform Bannerbear 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 Bannerbear MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Bannerbear.

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 Bannerbear action and event your agent gets out of the box.

Create Project

Creates a new Bannerbear project with the specified name and optional settings.

Create Signed Base

Tool to create a signed URL base for a template.

Create Template

Create a new blank template in a Bannerbear project.

Create Template Set

Tool to create a new template set by grouping multiple templates together.

Create Video Template

Tool to create a new video template for video generation in Bannerbear.

Create Webhook

Create a project-level webhook that fires for all events of a specific type.

Delete Template

Tool to delete a template referenced by its unique ID.

Delete Webhook

Tool to delete a webhook referenced by its unique ID.

Get Account Info

Retrieves Bannerbear account information including subscription plan, API usage, and quota limits.

Get Animated GIF

Tool to retrieve a single Animated Gif object by its unique identifier (UID).

Get Auth Status

Verify API authentication and check which project the API key is scoped to.

Get Available Fonts

This tool retrieves a list of all available fonts in Bannerbear.

Get Image

Retrieves a single Image object by its unique identifier (UID).

Get Project

Retrieves detailed information about a specific Bannerbear project by its unique identifier (UID).

Get Screenshot

Retrieve a single Screenshot object referenced by its unique ID.

Get Signed Bases

This tool retrieves a list of signed bases for a specific template.

Get Template

Tool to retrieve a single template by its unique ID with layer defaults.

Get Template Set Details

This tool retrieves detailed information about a specific template set using its unique identifier (UID).

Get Webhook

Retrieves a single Webhook object by its unique ID.

Hydrate Project

Hydrate a project by copying templates from another project.

Import Template

Tool to import templates from the Bannerbear template library or from other projects.

Join PDFs

Merges multiple PDF files into a single combined PDF document.

List Animated GIFs

Lists all animated GIFs in a Bannerbear project.

List Collections

Lists all collections in a Bannerbear project.

List Effects

Tool to list all available image effects in Bannerbear.

List Images

Lists all images in a Bannerbear project.

List Projects

Lists all projects in a Bannerbear account.

List Screenshots

Lists all screenshots in a Bannerbear project.

List Templates

This action retrieves a list of all templates available in your Bannerbear project.

List Template Sets

Tool to list all template sets inside a project with pagination support.

List Videos

This action retrieves a list of all videos created in your Bannerbear account.

List Video Templates

This action retrieves a list of all video templates available in your Bannerbear project.

Update Template Set

Tool to update a template set by modifying its list of templates.

FAQ

Frequently asked questions

With a standalone Bannerbear MCP server, the agents and LLMs can only access a fixed set of Bannerbear tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Bannerbear 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 Bannerbear tools.

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

Start with Bannerbear.It takes 30 seconds.

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

Start building