How to integrate Googlephotos MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Googlephotos Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Googlephotos to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Googlephotos agent that can find all photos from my last vacation, create a new album for 2024 events, upload these images to my family album, download the latest shared photo from friends through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Googlephotos account through Composio's Googlephotos 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 and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Googlephotos
  • Configure an AI agent that can use Googlephotos as a tool
  • Run a live chat session where you can ask the agent to perform Googlephotos operations

What is open-ai-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 Googlephotos MCP server, and what's possible with it?

The Googlephotos MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Photos account. It provides structured and secure access to your photo library, so your agent can organize albums, upload and manage media items, search your photos, and even download images on your behalf.

  • Effortless media uploads and organization: Instantly upload new photos or videos, add them to existing albums, and create new albums for specific events or trips—all through your AI agent.
  • Smart album and library management: List all your albums or fetch details for any album, making it simple for the agent to help you organize or locate collections of photos.
  • AI-powered photo search: Ask your agent to search your photo library using keywords, dates, or other criteria to quickly find specific images or memories.
  • Bulk media handling: Retrieve batches of photos or videos, add multiple media items to albums at once, or download images as files for sharing or backup.
  • Enhanced photo enrichment: Automatically enhance your albums by adding context, locations, or notes at specific positions—helping you curate richer stories from your memories.

Supported Tools & Triggers

Tools
Add EnrichmentAdds an enrichment at a specified position in a defined album.
Batch Add Media ItemsAdds one or more media items to an album in google photos.
Batch Create Media ItemsUnified action to upload media files and create them as items in google photos.
Batch Get Media ItemsReturns the list of media items for the specified media item identifiers.
Create AlbumCreates a new album in google photos.
Get AlbumReturns the album based on the specified albumid.
Download Photos Media ItemDownloads a media item from google photos and returns it as a file.
List AlbumsLists all albums shown to a user in the albums tab of google photos.
List Media ItemsLists all media items from a user's google photos library.
Search Media ItemsSearches for media items in a user's google photos library.
Update AlbumUpdates an album's title or cover photo in google photos.
Update Media ItemUpdates a media item's description in google photos.
Upload MediaUpload a media file to google photos.

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:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Googlephotos project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

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.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
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 Googlephotos.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Googlephotos Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["googlephotos"]
)

mcp_url = session.mcp.url

What is happening:

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

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Googlephotos. "
        "Help users perform Googlephotos operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "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 Googlephotos 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 dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Googlephotos operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Googlephotos.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Googlephotos and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["googlephotos"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Googlephotos. "
        "Help users perform Googlephotos operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

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

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.

How to build Googlephotos MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Googlephotos MCP with Claude Agent SDK

Google ADK

Google ADK

Use Googlephotos MCP with Google ADK

LangChain

LangChain

Use Googlephotos MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Googlephotos MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Googlephotos MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Googlephotos MCP with LlamaIndex

CrewAI

CrewAI

Use Googlephotos MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Googlephotos MCP?

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

Can I use Tool Router MCP with OpenAI Agents SDK?

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 Googlephotos tools.

Can I manage the permissions and scopes for Googlephotos while using Tool Router?

Yes, absolutely. You can configure which Googlephotos 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 Googlephotos 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