SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Bannerbear MCP with Pydantic AI

Connect Pydantic AI to Bannerbear MCP. Merge multiple marketing pdfs into one file, list all video assets created this week, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
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 Pydantic AI using the Composio tool router. By the end, you'll have a working Bannerbear agent that can create templates and template sets, list generated images and videos, fetch screenshots and GIFs, and join PDFs through natural language commands.

This guide will help you understand how to give your Pydantic AI 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

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Bannerbear
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Bannerbear workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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 projects, templates, generated media, fonts, and effects, so your agent can browse creative assets, inspect templates, organize template sets, create video templates, and merge PDFs on your behalf.

  • Project and usage overview: Have your agent list your projects, retrieve project details, and check your current plan, API usage, and quota limits.
  • Generated media retrieval: Let the agent find and inspect your images, videos, animated GIFs, screenshots, and collections.
  • Template discovery and setup: Direct your agent to browse templates, review their layer defaults, import templates, copy templates between projects, or create video templates.
  • Template set management: Instruct your agent to create, inspect, list, and update grouped template sets for coordinated content production.
  • Creative production resources: Have your agent list available fonts and image effects, or combine multiple PDF files into one document.

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:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Bannerbear
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
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

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Bannerbear
  • MCPServerStreamableHTTP connects to the Bannerbear MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Bannerbear
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bannerbear"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Bannerbear tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
bannerbear_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[bannerbear_mcp],
    instructions=(
        "You are a Bannerbear assistant. Use Bannerbear tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Bannerbear endpoint
  • The agent uses GPT-5 to interpret user commands and perform Bannerbear operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Bannerbear.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Bannerbear API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Bannerbear and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Bannerbear
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bannerbear"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    bannerbear_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[bannerbear_mcp],
        instructions=(
            "You are a Bannerbear assistant. Use Bannerbear tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Bannerbear.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Bannerbear through Composio's Tool Router. With this setup, your agent can perform real Bannerbear actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Bannerbear for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
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

Permanently delete a template from a Bannerbear project by its unique ID.

Delete Webhook

Delete a webhook 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 a Bannerbear project by UID, including its name, creation date, template count, and feature settings.

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

Retrieve a template by its unique ID, including its dimensions and available modifications.

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

Hydrates a project by copying all templates from a source project or selected templates by UID.

Import Template

Imports publicly available templates into a project using publication IDs from the Bannerbear library or shared publications.

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 a page of 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

List templates in a Bannerbear project, with pagination and optional tag or partial-name filters.

List Template Sets

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

List Videos

List a page of videos in a Bannerbear project.

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.

FRAMEWORKS

How to build Bannerbear MCP Agent with another framework

Claude Code logo

Claude Code

Use Bannerbear MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bannerbear MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Bannerbear MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Bannerbear MCP with Claude Agent SDK

Codex logo

Codex

Use Bannerbear MCP with Codex

OpenClaw logo

OpenClaw

Use Bannerbear MCP with OpenClaw

Hermes logo

Hermes

Use Bannerbear MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Bannerbear MCP with Atomic Agent

Google ADK logo

Google ADK

Use Bannerbear MCP with Google ADK

LangChain logo

LangChain

Use Bannerbear MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Bannerbear MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Bannerbear MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Bannerbear MCP with LlamaIndex

CrewAI logo

CrewAI

Use Bannerbear MCP with CrewAI

AutoGen logo

AutoGen

Use Bannerbear MCP with AutoGen

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. Pydantic AI 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