Outline Count Studio

Live

Count and outline objects in a photo or short video clip.

musemuse-outline-count-studio.vercel.appOpen

Get it

Connect it to any app that speaks MCP. It has 1 tool: count_objects. No sign-in.

Muse app: add this URL as a custom connector.
Claude Code: claude mcp add --transport http outline-count-studio https://muse-muse.vercel.app/api/mcp/outline-count-studio
Anything else: add it as a remote server over streamable HTTP.

Each line is what the check ran on, and no more.

This is a model's opinion, not proof.

Nothing here should be taken as tested.

Not checked Whether its answers are true
Not checked ChatGPT: only a person with an account can test it
Not checked Installing the Claude plugin or the Muse gadget pack on a real device
Not checked No Prove it run: nothing it comes with was run for real

Rebuild of a Meta developer video demo that counts and outlines things in photos and short clips

SAM 3.1Segments and counts the named objects in a photo or short clip, returning boxes and masks for the outlines

Prompt must be one short noun phrase per run. Lists, questions and negation are not supported.
At most 16 objects per call. Crowded scenes or hidden objects will be missed or merged.
Video must be MP4 or MOV up to 15000 frames. Video billing has a 50 frame minimum.
Requests are capped near 4.5 MB. Larger files upload to temporary storage and are deleted after 24 hours.
No database or accounts. History stays in the browser only.

Add it in the Muse app as a custom connector. It exposes 1 action: count_objects.

Muse Code made 69 tool calls and 18 edits across 18 files (+1112 −32).
npm run verify passed on the first try.
Screenshot judge: pass. Final screen shows Found 6 apples with boxed outlines over the photo.
Built in 6 min for about $1.10 in model calls (est.).
How it was built: 69 tool calls, 18 edits touching 18 files { Read text file `inspo/README.md`. Read text file `musemuse.schema.json`. Read text file `app/globals.css`. Read text file `package.json`. <read-skill-result name="meta-sam" status="ok"> <read-skill-result name="verify" status="ok"> <read-skill-result name="product-ui" status="ok"> { Read text file `lib/meta/client.ts`. Read text file `lib/meta/parts.ts`. Read text file `lib/meta/media.ts`. Read text file `lib/meta/json.ts`. Read text file `components/FilePicker.tsx`. Read text file `components/ModelChip.tsx`. Read text file `components/Footer.tsx`. Read text file `lib/client/upload.ts`. Read text file `lib/client/resize.ts`. Read text file `tests/smoke.spec.ts`.