MCP App Store

Overview

Auto is a smart camera app. Connect to Auto to use photos from the Auto iOS App in ChatGPT. Search by content, location, time. Auto understands what is in your photos, your ChatGPT and Agents use them.

Tools

display_photo

ChatGPT
Display a single photo to the user as an embedded MCP App. Renders the image with its title and links to open or download the original. Prefer this over describing a photo in text or calling get_photo / get_photo_image whenever the user asked to see a photo. Returns an error if the photo is missing or not owned by the authenticated user.

display_photos_grid

ChatGPT
Display one or more photos to the user as an embedded MCP App in a responsive grid. Each card shows the photo title and links to open or download the original. Prefer this (or display_photos_carousel) over listing photo metadata in text whenever the user asked to see photos — pipe ids from list_photos / search_photos straight into this tool.

get_photo

ChatGPT
Fetch a single photo's metadata by id, including its memory-derived descriptions. Returns an error if the photo does not exist or is not owned by the authenticated user. To show the photo to the user, call display_photo instead — this tool is for when the model needs the metadata itself.

get_photo_image

ChatGPT
Fetch a single photo's image bytes as inline base64-encoded content for the model to see. The entire response is buffered, so call sparingly — photos larger than 10 MB are rejected. To show the photo to the user, call display_photo instead; only use this tool when the model itself needs to inspect the image pixels.

list_photos

ChatGPT
List the authenticated user's photos in reverse chronological capture order, optionally filtered by date range and/or a (lat, lng, radius) bounding circle. Returns metadata only. To show the photos to the user, pass the resulting ids to display_photos_grid (multiple photos) or display_photo (one photo) rather than describing them in text.

search_photos

ChatGPT
Search the authenticated user's photos. With query, runs semantic vector search over photo descriptions. Without query, returns photos matching the structured filters. All filters compose. Returns metadata only. To show the photos to the user, pass the resulting ids to display_photos_grid (multiple photos) or display_photo (one photo) rather than describing them in text.

Capabilities

Interactive

Example Prompts

Click any prompt to copy it.

App Stats

7

Tools

3

Prompts

ChatGPT

Platforms

Works with

ChatGPT

Data refreshed daily