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)
AI UGC videos of your store's products: read a product, write 3 scripts, make the video.
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://app.sayitagain.ai/mcpRun this in your terminal
claude mcp add --transport http sayitagain https://app.sayitagain.ai/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"sayitagain": {
"url": "https://app.sayitagain.ai/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": {
"sayitagain": {
"type": "http",
"url": "https://app.sayitagain.ai/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://app.sayitagain.ai/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.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 6, 2026
The registry name was verified against the domain sayitagain.ai (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
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 1 of 1 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 (1.0.1) 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:★ 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.
Say It Again makes AI UGC videos for online stores from their product pages. A generated presenter holds, uses or wears the product and speaks a script written from the page. This remote MCP server lets an AI assistant do the same with your Say It Again account: read a product, write three scripts, quote a video's price in credits, make the video and follow it until it is ready.
This repository holds no server code. The server is hosted by Say It Again, and this README says what it does and how to connect to it. Full reference: https://sayitagain.ai/docs/api
https://app.sayitagain.ai/mcpAuthorization: Bearer ai.sayitagain/sayitagainThe API and the MCP server come with a plan: Lite, Starter, Growth or Scale. They are not in the free trial. Plans and prices: https://sayitagain.ai/pricing
To use a key: sign in to Say It Again as the owner of your team, open Settings, then API, and press Create key. The key is shown once. A key acts for your whole team and spends its credits, so keep it secret, and revoke it there at any time.
claude mcp add --transport http sayitagain https://app.sayitagain.ai/mcp \
--header "Authorization: Bearer $SIA_KEY"
Or leave out the header and sign in when Claude Code asks.
In .vscode/mcp.json:
{
"inputs": [ { "type": "promptString", "id": "sia-key", "description": "Say It Again API key", "password": true } ], "servers": { "sayitagain": { "type": "http", "url": "https://app.sayitagain.ai/mcp", "headers": { "Authorization": "Bearer ${input:sia-key}" } } } }
Add a remote MCP server with the address https://app.sayitagain.ai/mcp. Where the client takes an API key or a bearer token, give it your key.
Every tool is free except make_video, change_video, make_longer and another_language, which spend the team's credits.
| Tool | What it does |
|---|---|
get_balance | The team's credits, its plan, and how many script writes it has left. |
read_product | Reads a product's page from its link: name, price, description, benefits, photos, and an id for the other tools. |
write_scripts | Writes three scripts for a video of a product, from what read_product read. |
get_scripts | The scripts write_scripts wrote, once they are ready. |
quote_video | What a video with these choices costs in credits, and whether the balance covers it. |
make_video | Makes a UGC video of a product. Spends the price quote_video gave, refunded if the video fails. |
get_video | How a video is going, and its download link once it is ready, with the steps it offers next. |
list_videos | The team's videos, newest first. |
list_presenters | The presenters a video can be made with. |
list_ads | The Meta Ad Library ads the team's store already holds, to build a video like one of them. |
describe_presenter | Draws a presenter of the team's own from a description of how they look. |
get_described | How a drawing is going, with its pictures once it is ready. |
keep_presenter | Keeps one of those pictures as one of the team's presenters. |
set_presenter_voice | Sets the voice a described presenter speaks in. |
change_video | Changes a finished video as you ask, into a new video beside it. Spends credits, refunded if it fails. |
make_longer | Makes a finished video longer, with new lines from the product page. Spends credits, refunded if it fails. |
another_language | Makes a finished video again in another language. Spends credits, refunded if it fails. |
other_sizes | Lays a finished video out in another size. Free. |
Each tool that spends takes the price in credits that quote_video or the video's next steps gave, and an idempotency key, every time: a price that is no longer right is refused and nothing is spent, and a retry with the same key spends nothing more.
Ask your assistant, for example:
Requests per minute and presses per day are listed on https://sayitagain.ai/docs/api, as are the errors each tool can answer. Videos made by Say It Again carry Content Credentials.
support@sayitagain.ai. Say It Again is made by Apolonis Social Media Management Services - FZCO, Dubai, United Arab Emirates. https://sayitagain.ai