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)
Quote Seedance video credits, create approved videos, and read your private tasks and balance.
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.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http superseedance https://superseedance.si/api/mcp --header 'Authorization: Bearer {api_key}'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"superseedance": {
"url": "https://superseedance.si/api/mcp",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}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": {
"superseedance": {
"type": "http",
"url": "https://superseedance.si/api/mcp",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}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.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
The server asks you to sign in before it lists its tools.
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 name was verified against the domain superseedance.si (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 300 ms (HTTP 401)
Declares OAuth sign-in, so your AI app can take you to log in
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 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.
You need to fill in: Authorization
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 (1.0.0) reached the registry 15 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:↓ Downloads per weeki★ 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.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Practical Seedance video guides, complete prompts and original examples from SuperSeedance.
简体中文
SuperSeedance is an independent AI video workspace for creating from text or images with Seedance 2.5. It brings prompts, private reference images, credit estimates and saved videos into one place, with an interface in 20 languages.
| What you want to do | Guide |
|---|---|
| Make your first video | Getting started · Full website guide |
| Check an image and compare first-frame / Reference framing | Image diagnostics guide · Open the tool |
| Preview product-ad wording and revise from the same source | Workflow and validation scope · Free wording preview |
| Prepare a short English dialogue comparison | Workflow and validation scope · English audio guide |
| Write camera, action or animation prompts | Eight prompts and example videos |
| Reuse a character across shots | Character reference workflow |
| Fix weak motion, distortion or task errors | Video troubleshooting |
| Plan duration, resolution and budget | Video cost guide |
| Integrate from your backend | API notes · API reference |
| Connect a compatible server-side MCP client | MCP connection and tools |
| Plan locally with a Claude Skill | Install and use the video planner · Website guide |
| Decide whether to test in Draft mode | Draft mode and staged budget |
| Plan a consistent three-shot animated story | 3D story workflow |
The prompt guide pairs eight original Seedance 2.5 clips with their complete prompts and generation settings: rainy-night parkour, a cloud-city flight, anime skating, an ink-wash whale, solo dance, clay animation, a forest adventure and liquid metal.
The submitted settings for these eight examples were text-to-video, six seconds, 720p, 16:9, no audio and no draft mode. Preview edits do not change those source-generation settings. A prompt is a reproducible starting point; it does not guarantee an identical output.
Choose text or image input, describe one scene and its movement, select supported settings, review the studio-credit quote, then submit and track the task in My Creations. Generation requires a verified account, sufficient credits and an available service.
Credit purchases are not yet available as of October 24, 2026. Existing guides and public examples remain accessible. Check the pricing page for the current purchase status.
This documentation is maintained for SuperSeedance. The platform is independently operated by 幸会新知科技(深圳)有限公司 and is not affiliated with ByteDance. This repository contains guides; the hosted application source code is not included.
About · Contact · Terms · Privacy
Sample videos are presented for demonstration; viewing this repository does not grant a commercial redistribution license for them. Use your own or authorized input material and review the applicable terms before publishing generated work.
The product-ad wording preview and expanded optional measurement are live. The account-initialization input issue was fixed and passed eight additional live checks. The 856-test suite, typecheck, build and three isolated CTA renders passed without new generation jobs or credit entries. Local and production English/Chinese browser checks passed at 320/360/390/430/1280px without horizontal overflow; the production check retained an existing signed-in session, used measurement exclusion and submitted no upload, generation or ad assembly. Acceptance aggregate counts showed no new assets, jobs, ads or credit spending. These were viewport checks, not physical-device tests; the three renders were local only. See the product-ad validation scope.
Updated October 27, 2026. The image-diagnostics tool is live, with both first-frame and Reference preparation flows checked online without uploading an image or submitting a generation. Local checks and signed-in mobile-width browser checks passed, with no new saved assets, generation tasks or credit spending during acceptance. The checks used resized browser viewports, not physical iOS/Android devices or a real-user study. The live website is the source for current availability and prices.
The English dialogue preparation tool is live and passed local and online free-flow and resized-phone-viewport checks. It prepares A/B prompts and a manual review plan without generating audio. Both creator handoffs were checked; acceptance aggregates showed no new jobs or credit spending. No audio sample, listening result or repair rate is claimed. See the validation scope.