Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Description from the maker (original English)
Photo shoots of you from your saved selfies: pick a pack, shoot, edit.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://luala.app/mcpRun this in your terminal
claude mcp add --transport http luala https://luala.app/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"luala": {
"url": "https://luala.app/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"luala": {
"type": "http",
"url": "https://luala.app/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://luala.app/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
list_packsLists Luala's photo packs (a themed shoot of several photos of the user, made from their selfies) and mixes (one photo from each of several packs), with what all of a pack's photos cost and the price of one: a shoot can be any of a pack's shots, down to a single photo. Optionally
get_packA pack's or mix's options (outfit, place, light, shots, shape and the attribute pickers), with ids, labels and defaults, and its price per photo. Each shot is one photo, and the user may pick any of them, from one to all (the default). start_shoot takes these ids.
start_shootStarts a shoot of a pack from the user's saved selfies, paid from their credits: one photo per picked shot, at the price get_pack gives. Unless the user has said, offer them the whole pack or only the shots they want, even one. Tell the user the price first and pass it as max_cre
get_shootA shoot's photos: each one's id, whether it is ready, still working or failed (failed photos are refunded), each one's link in the Luala app (the link to give the user), and the shoot's page there; previews of the ready ones once none is working. While photos are working it waits
editMakes an edited copy of one of the user's photos, paid from their credits. type change keeps the pose and framing and changes any of: outfit and place (ids from get_pack of the photo's pack), light, the attributes, and text, up to 300 characters of what to change. type zoom_out s
zoom_inCuts a frame of the given shape out of one of the user's photos and upscales it to a full photo, paid from their credits. x, y and w are the frame's left edge, top edge and width as fractions of the photo (0 to 1); left out, the largest frame is centred. Pass the price the user a
upscaleUpscales one of the user's photos to 1K, 2K or 4K, paid from their credits. A photo is offered only the sizes larger than it and at most 4× its size; its prices from get_shoot or list_photos name them. Pass the price the user agreed to as max_credits. If a call to this tool got n
rerollMakes the same photo again, a new take of the same look, paid from the user's credits. Pass the price the user agreed to as max_credits: the photo's prices from get_shoot or list_photos name it. If a call to this tool got no answer, it may already have started: check list_photos
remove_backgroundCuts the person out of one of the user's photos, paid from their credits: on a clear (transparent) backdrop unless backdrop names a colour, #rrggbb (the app offers #ffffff, #e9e7e3, #3a3a3c, #000000, #1f2f4d, #bcd7ee, #f2e8d5, #b9c8b0). On a photo that is already a cutout it lays
remove_objectsTakes what description names out of one of the user's photos, paid from their credits, and fills where it was from what is around it; nothing else in the photo changes. Describe it as the user did, in any language (the people behind me, the bin on the left, the sign and the cable
replace_backgroundPuts the person in one of the user's photos somewhere else, keeping their pose and framing, paid from their credits: scene is one of the app's scenes, or text says the place in up to 300 characters; a scene wins when both come. Pass the price the user agreed to as max_credits: th
light_cameraChanges the light, the camera or the look of one of the user's photos, paid from their credits: at most one pick per group (light, lens, angle, focus, look), and/or text, up to 300 characters of what to change. What is not picked stays as it is. light and look keep the pose, fram
restoreRepairs an old or damaged photo of the user's (a photographed print, most often one from list_photos with uploads), paid from their credits: repair fixes scratches, tears and stains, faces enhances them, colourise adds colour to a black and white one. size 1K is Standard, 2K High
blur_facesHides every face in one of the user's photos, as a new photo, paid from their credits: effect blur or pixelate, strength 0 (light) to 100 (strong). The faces are found by Luala; with none found nothing is started or charged. To keep some faces sharp or hide one it missed, the use
combineAdds the main subject of another of the user's photos (with_photo_id: an object or a person, a cutout works well) into one of their photos, keeping its scene, framing and light, paid from their credits. with_photo_id may not be a selfie, nor photo_id itself. Pass the price the us
try_onPuts the clothes another of the user's photos shows (with_photo_id) on the person in one of their photos, paid from their credits; part top or bottom takes only that part of the outfit. with_photo_id may not be a selfie, nor photo_id itself. Pass the price the user agreed to as m
list_photosWith ids, those photos (up to 10), with a preview of each ready one once none is working: how to fetch an edit's result. While one is working it waits up to 25 seconds for it. Without, the user's latest shoots, newest first, five at a time; pass the answer's next as before for th
add_photoAdds one photo to the user's My photos in Luala, free, so it can be edited: an old print to restore, clothes to try on, a photo to change. The answer is the saved photo with its photo_id and edit prices: when the user asked for an edit of it, tell them that edit's price, and once
add_selfieAdds one selfie to the user's selfie set in Luala, which shoots are made from, free: one face, clearly visible, up to 15 selfies in the set. Pass the file the user attached as photo. If you can't, but the file is in your sandbox, call with its content_type (image/jpeg, image/png
upload_statusFor Luala's widget: whether the file staged at key was saved by add_photo or add_selfie (tool). Read-only.
balanceThe user's credit balance, about how many photos it buys, and where to buy more.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry lists no source repo, so we cannot match the publisher (luala.app) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 85 ms (HTTP 200)
No sign-in needed
Read 21 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.19.0) reached the registry 4 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
No README found in the repo