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)
Generate and edit images, video and audio: 300+ AI models, video tools, voice cloning, transcripts.
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://mcp.aitopia.ai/mcpRun this in your terminal
claude mcp add --transport http aitopia https://mcp.aitopia.ai/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"aitopia": {
"url": "https://mcp.aitopia.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": {
"aitopia": {
"type": "http",
"url": "https://mcp.aitopia.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://mcp.aitopia.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 aitopia.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 (1.0.0) reached the registry 31 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.
AI agent skills for creating, editing and analyzing images, video, voiceovers and music with AITOPIA — plus AITOPIA's production playbooks for product ads, UGC videos, short-form videos, YouTube thumbnails and brand kits. Works with Claude Code, Codex, Cursor and other agents that load Markdown skills, and with any MCP client through the AITOPIA server.
Everything runs on your AITOPIA account through the AITOPIA MCP server (https://mcp.aitopia.ai/mcp). There is nothing to install locally: the first AITOPIA action opens a browser sign-in, and every result is saved to your account, where you can keep working on it.
Pick one. The plugin installs (Claude Code, Codex, Cursor) connect the AITOPIA server for you.
/plugin marketplace add AITOPIAai/skills
/plugin install aitopia@aitopia
npx skills — cross-agentnpx skills add AITOPIAai/skills
Installs the skills into Claude Code, Codex, Cursor and many other agents. Connect the AITOPIA server once as well (see INSTALL.md).
codex mcp add aitopia --url https://mcp.aitopia.ai/mcp
codex mcp login aitopia npx skills add AITOPIAai/skills --agent codex
Gemini CLI (server + playbooks):
gemini extensions install https://github.com/AITOPIAai/skills
Any other MCP client: add the remote server https://mcp.aitopia.ai/mcp (Streamable HTTP, OAuth sign-in).
Settings → Connectors → Add custom connector → https://mcp.aitopia.ai/mcp, then sign in with AITOPIA. Generated images and videos show inline in the conversation.
Go to chatgpt.com/plugins → Add → Create MCP App, enter https://mcp.aitopia.ai/mcp, then sign in with AITOPIA. Developer mode is no longer needed.
npm i -g aitopia
aitopia login aitopia image "a red paper boat on a pond" aitopia dub video.mp4 --to Spanish --dry-run
aitopia --help lists every command (image, video, audio, edit, analyze, transcribe, dub, upload, models…).
More options in INSTALL.md. Agent-driven install (paste into your agent): INSTALL_FOR_AGENTS.md.
| Skill | What it does |
|---|
| aitopia-generate /aitopia:aitopia-generate | Images, video, voiceover, music and sound effects. Picks the model for the job the way AITOPIA does; several images come back together in one call. | | aitopia-edit /aitopia:aitopia-edit | Join clips, add voiceover or music, trim, resize to 9:16 / 16:9 / 1:1, text and logo overlays, subtitles, fades, speed changes, mute / extract / normalize audio, animate a still image. | | aitopia-upload /aitopia:aitopia-upload | Send a local photo, video, audio file or document to AITOPIA (up to 95 MB; 200 MB from a public URL). | | aitopia-product-ad /aitopia:aitopia-product-ad | Product commercial from a product photo: hero keyframe, motion, voiceover, music. | | aitopia-ugc-video /aitopia:aitopia-ugc-video | Creator-style UGC ad — testimonial, before/after, hook video, phone-shot feel. | | aitopia-short-video /aitopia:aitopia-short-video | TikTok / Reels / Shorts, launch and promo videos end to end. | | aitopia-youtube-thumbnail /aitopia:aitopia-youtube-thumbnail | High click-through YouTube thumbnails: bold subject, contrast, big readable text. | | aitopia-brand-kit /aitopia:aitopia-brand-kit | Logo direction, color palette, typography and usage rules. |
The second line is the command in the Claude Code plugin; with npx skills the command is the skill name, e.g. /aitopia-generate.
Agents also use the skills on their own when a request fits. The playbooks behind the workflow skills live on AITOPIA and are loaded at run time, so they improve without reinstalling anything.
The skills chain: aitopia-upload turns a local file into an asset URL that every other skill accepts; aitopia-generate produces the stills and clips that aitopia-edit assembles; the workflow skills (product-ad, ugc-video, short-video, youtube-thumbnail, brand-kit) drive both.
Ask your agent what is in a video, image or audio file and it uses AITOPIA's analyze_media tool. The agent watches the video and listens to it, then answers:
aitopia-edit.aitopia-generate.It answers in any language. Try it in Claude, ChatGPT, Cursor or Codex:
Analyze this video and list every scene with its time: <video URL>
Score this ad and tell me how to improve the first 3 seconds: Write a prompt that re-creates this image:
A video can be up to 2 MB for now. One analysis costs about 3 credits, and a failed run is not charged. Ask for the price first and the agent checks it with dryRun without running anything. The same analysis is in the AITOPIA CLI (aitopia analyze clip.mp4 --mode scenes) and in AITOPIA chat.
| What you want | Skill | Note |
|---|---|---|
| An image, or several options of one | aitopia-generate | Up to 4 images in one call, shown side by side |
| A short video from a prompt or a photo | aitopia-generate | Long runs finish in the background; the result appears when ready |
| Voiceover, music or a sound effect | aitopia-generate | Voice and music use different models |
| Use a photo or video from your computer | aitopia-upload | Then pass the asset URL to any skill |
| Join clips, add music or voiceover | aitopia-edit | video_editor also joins audio files end to end |
| Reframe for Reels / TikTok / YouTube | aitopia-edit | resize with fit cover / contain |
| Titles, captions, logo, subtitles | aitopia-edit | add_text, overlay, subtitle |
| Remove a background, upscale, restore | aitopia-generate | AITOPIA picks a suitable model or store agent |
| What is in a video, image or audio | analyze_media tool | Summary, speech, on-screen text, audio; video up to 2 MB |
| Every scene of a video with its time | analyze_media tool | mode: scenes; then cut with aitopia-edit |
| Review an ad (score, hook, CTA) | analyze_media tool | mode: ad_review |
| A prompt that re-creates a video or image | analyze_media tool | mode: prompt; then aitopia-generate |
| Product commercial | aitopia-product-ad | Starts from the product photo |
| UGC ad | aitopia-ugc-video | Creator-style, phone-shot feel |
| YouTube thumbnail | aitopia-youtube-thumbnail | Several variants to choose from |
| Brand identity | aitopia-brand-kit | Logo direction, palette, type |
Recipes that combine skills: COOKBOOK.md.
Generation spends AITOPIA credits from your account; editing and uploads are cheap or free. If a run needs more credits, the result links to aitopia.ai/pricing.
MIT — see LICENSE.