Google Photos MCP server
13 operations0 webhooks
Read albums and media items, upload photos and videos, and manage album membership through the Google Photos Library API.
Try Google Photos with your agent
Connect Google Photos, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in Google Photos on my account, then run one read-only example and show me the result.
Google Photos tools and triggers
Tools are what your agent can do in Google Photos through Corsair's MCP server. Triggers are the Google Photos events a routine can start from.
Albums
- Add EnrichmentWrite
Add a text note or a location to an app-created album, at a chosen position
albums.addEnrichment
- Batch Add Media ItemsWrite
Add up to 50 media items to an app-created album
albums.batchAddMediaItems
- Batch Remove Media ItemsDestructive
Remove up to 50 media items from an album. The items stay in the library, so this is reversible by adding them back
albums.batchRemoveMediaItems
- CreateWrite
Create an album with a title
albums.create
- GetRead-only
Read one album this app created
albums.get
- ListRead-only
List the albums this app created; since March 2025 the API reads nothing else
albums.list
- UpdateWrite
Rename an app-created album (sends the title update mask)
albums.update
Media Items
- Batch GetRead-only
Read up to 50 app-created media items by id, with a per-id status
mediaItems.batchGet
- CreateWrite
Upload bytes and create up to 50 media items, optionally in an album; uploads count toward the user's Google storage past 25MB
mediaItems.create
- GetRead-only
Read one media item this app created
mediaItems.get
- ListRead-only
List the media items this app created, 25 per page by default
mediaItems.list
- SearchRead-only
Search the media items this app created with date, content, feature and media-type filters, or list one app-created album
mediaItems.search
- UpdateWrite
Change an app-created media item's description, the only editable field
mediaItems.update
Connect Google Photos to Claude, ChatGPT or Cursor
- 1
Connect Google Photos in Corsair
Sign in to Google Photos once in Corsair. Corsair stores the credential encrypted and makes the Google Photos API calls for your agent, so it never goes into a prompt or a config file. Connect Google Photos
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Google Photos. On a ChatGPT personal plan, connect Google Photos here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Google Photos's read and write operations run right away and its 1 destructive operation waits for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.
FAQ
Install corsair and @corsair-dev/googlephotos, add the Google Photos plugin, and connect with OAuth. Then call methods like corsair.googlephotos.api.albums.addEnrichment() from your app. Corsair stores tokens, and keeps each tenant isolated.
Yes. Google Photos needs an OAuth app with scopes that match what you automate. Register the app in Google Photos, configure redirect URLs, then connect through Corsair or managed OAuth in Hub.
Yes. One Corsair client can hit Google Photos, GitHub, Notion, Stripe, and the rest. Trigger Google Photos from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for read albums and media items, upload photos and videos, and manage album membership through the Google Photos Library API. Common builds include sync jobs, admin tooling, and agents that call Google Photos APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Google Photos API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/googlephotos in the open repo. When Google Photos ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your Google Photos data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Google Photos data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put Google Photos on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 1 destructive Google Photos operation. You can change a link's mode at hub.corsair.dev/me.