# Build a Google Photos agent with Claude Code

> Have Claude Code build a Google Photos agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.

- Page: https://www.agent200.com/connectors/google-photos/framework/claude-code/
- Connector: [Google Photos](https://www.agent200.com/connectors/google-photos.md)
- Framework: Claude Code
- Updated: 2026-11-18

## Instructions for AI agents

Goal: connect Google Photos to Claude Code with Agent200.
Guide: https://www.agent200.com/connectors/google-photos/framework/claude-code/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Make sure Google Photos is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's Google Photos account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Google Photos.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "google_photos" in the tools. The model decides when a Google Photos tool is needed; Agent200 executes the call.
7. Check it works with this request: "Show the albums you have made for me"
   What should come back:
   - A result from that user's own Google Photos account.
   - Behind the scenes, Claude Code calls `google_photos_list_albums`.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Google Photos, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## Overview

This guide has Claude Code build a Google Photos agent with the Agent200 SDK, in your own project. When you finish, your agent can call the Google Photos tools for each of your users.

Claude Code writes the code from the steps below; Agent200 runs the Google Photos calls with each user's own connection and handles the OAuth flow and the tokens. You do not build or maintain a Google Photos integration.

- **Connector:** [Google Photos](https://www.agent200.com/connectors/google-photos/)
- **Works with:** Claude Code · Coding agent, with the SDK
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [5 tools](https://www.agent200.com/connectors/google-photos/framework/claude-code/#tools)
- **Model in examples:** `openai/gpt-5.6-sol`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **Google Photos enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **An end user with a Google Photos account.** They approve access once, on Google Photos's own page.
- **Claude Code in your project.** It writes the code with the Agent200 SDK; you review it.

## Connect Google Photos to Claude Code

### Step 1: Create your Agent200 API key

Open the API keys page in the Agent200 dashboard and choose Create an API key. Copy the key and store it as an environment variable, AGENT200_API_KEY, or in your secrets manager. One key covers Google Photos and every other connector and model enabled for your project. Keep it out of chats, prompts and source control.

Create an API key: https://agent200.com/platform/apikeys/

File `.env`:

```bash
# Keep the key out of your code, prompts and chats.
export AGENT200_API_KEY="paste-your-key-here"
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Give this guide to Claude Code

Start Claude Code in your project and paste the agent brief from this page, or give it the address of this guide's Markdown version. Claude Code follows the steps below in order: the SDK, the Google Photos connection and the first request. Review the code it writes before you run it.

### Step 3: Set up the Agent200 SDK

Add the SDK to your project and create a client with the key from the environment.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 4: Let your user connect Google Photos

Each end user authorizes their own Google Photos account once, through managed OAuth. If the user has not connected yet, Agent200 returns an authorization link: show it to them, and they approve access on Google Photos's own page. Agent200 handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Google Photos account, once.
const connection = await agent200
  .user("user_123")
  .connect("google_photos");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 5: Run with the Google Photos tools

Name the user, the model and Google Photos in the tools. The model decides when a Google Photos tool is needed, and Agent200 executes the call with the user's own connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Upload these receipts to a new album called Expenses",
    tools: ["google_photos"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Test your connection

Ask: "Show the albums you have made for me"

What should come back:

- A result from that user's own Google Photos account.
- Behind the scenes, Claude Code calls `google_photos_list_albums`.

If you get an authorization link instead, the user has not connected Google Photos yet. Show them the link, then run the request again.

## Google Photos tools Claude Code can call

- **Upload media** (`google_photos_upload_media`, write): Upload a photo or video to the user's library.
- **Create an album** (`google_photos_create_album`, write): Create a new album.
- **Add to an album** (`google_photos_add_to_album`, write): Add uploaded items to an album the connection created.
- **List albums** (`google_photos_list_albums`, read): List the albums the connection created.
- **List media** (`google_photos_list_media`, read): List the photos and videos the connection uploaded.

## How it works

1. **Your app sends the request.** It calls Agent200 with the model, instructions, the input, the end user's id and the Google Photos tools.
2. **The model picks a tool.** The model decides whether a Google Photos tool is needed, and with which arguments.
3. **Agent200 runs the call.** It uses that user's own Google Photos connection, within the endpoints and scopes your project allows, and returns the result to the model.
4. **Your app gets the result.** Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

**Each user's own connection.** Connections belong to individual end users. A request for one user never reaches another user's Google Photos account.

**Permissions at every level.** Your project settings decide what the agent may request, the end user decides what they authorize, and Google Photos enforces what its API grants.

## Troubleshooting

### The request says Google Photos authorization is required

The end user has not connected Google Photos yet, or the connection needs to be approved again. Agent200 returns an authorization link: show it to the user, let them approve access on Google Photos's own page, then run the request again.

### Claude Code does not use the Google Photos tools

Check that Google Photos is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming Google Photos in the request, or in the instructions, also helps the model choose the right tool.

### A tool call is refused or returns less than expected

Agent200 runs only what your project allows (services, endpoints and scopes), and Google Photos returns only what the end user authorized. Widen the endpoints or scopes in the dashboard if the agent needs more, then ask the user to connect Google Photos again so they can approve the new access.

### The results come from the wrong account

Every request names an end user (`user_123` in the examples). Pass the id of the person your agent is working for: Agent200 then uses only that user's Google Photos connection, never another user's.

### The API key was pasted into a chat or committed

Create a new key on the [API keys page](https://agent200.com/platform/apikeys/), update `AGENT200_API_KEY` wherever your app reads it, and stop using the old one. Keep keys in environment variables or a secrets manager, never in prompts, chats or source control.

## Use Google Photos with another framework

- [Google Photos + Claude](https://www.agent200.com/connectors/google-photos/framework/claude.md)
- [Google Photos + ChatGPT](https://www.agent200.com/connectors/google-photos/framework/chatgpt.md)
- [Google Photos + Muse](https://www.agent200.com/connectors/google-photos/framework/muse.md)
- [Google Photos + Grok Bot](https://www.agent200.com/connectors/google-photos/framework/grok-bot.md)
- [Google Photos + OpenAI Dots](https://www.agent200.com/connectors/google-photos/framework/openai-dots.md)
- [Google Photos + Claude Duet](https://www.agent200.com/connectors/google-photos/framework/claude-duet.md)
- [Google Photos + Hermes Agent](https://www.agent200.com/connectors/google-photos/framework/hermes-agent.md)
- [Google Photos + OpenClaw](https://www.agent200.com/connectors/google-photos/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
