SmugMug for AI agents
SmugMug is a platform where photographers host, organize, and sell their photo and video galleries, with folders and albums structured for client delivery. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in SmugMug.
Pull images from a client album
List the images in an album to confirm a client gallery is complete before sharing the link.
Check album details before publishing
Get an album's settings and highlight image as a read-only check before a photographer shares it publicly.
Search a photographer's full catalog
Search a user's content across folders to locate a specific photo without browsing every album.
25 SmugMug actions, graded by risk.
Every SmugMug action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
23Look things up. Allowed by default.
- smugmug.get_userGet User
- smugmug.get_albumGet Album
- smugmug.get_imageGet Image
- smugmug.get_album_imageGet Album Image
- smugmug.get_image_sizesGet Image Sizes
- smugmug.get_node_parentGet Node Parent
- smugmug.get_album_imagesGet Album Images
- smugmug.get_node_parentsGet Node Parents
- smugmug.get_user_profileGet User Profile
- smugmug.list_child_nodesList Child Nodes
- smugmug.get_folder_albumsGet Folder Albums
- smugmug.get_user_featuresGet User Features
- smugmug.get_folder_detailsGet Folder Details
- smugmug.get_image_metadataGet Image Metadata
- smugmug.get_user_bio_imageGet User Bio Image
- smugmug.get_user_root_nodeGet User Root Node
write
2Create and change things. Allow, or ask the user first.
- smugmug.unlock_userUnlock User Site
- smugmug.unlock_albumUnlock Album
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
SmugMug in three steps.
- 01Your users connect SmugMugThey add their SmugMug api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “unlock User Site” can wait for the user to approve.
- 03Any agent can actYour agent calls SmugMug through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('smugmug', { read: 'allow', write: 'ask', // unlock_user destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How SmugMug connects.
Users add their SmugMug api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same SmugMug connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use SmugMug from any agent.
SmugMug and Arc0, answered.
Can I use SmugMug with Claude, ChatGPT or Cursor?
Yes. Connect SmugMug to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the SmugMug actions you allow.
How do users connect SmugMug?
Users add their SmugMug api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which SmugMug actions can my agent take?
25 in total: 23 read, 2 write and 0 destructive, such as “unlock User Site”. Your policies decide which of them each agent may call.
Can I make my agent read-only in SmugMug?
Yes. Allow read actions and deny writes in the SmugMug policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call SmugMug too?
Yes. The same SmugMug connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug SmugMug into your agent.
Your users connect SmugMug once, under your brand. Your agent gets 25 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan