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)
Record your Mac screen, face and voice, edit the video by its transcript, and share a link.
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.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
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.
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 one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
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.
Runs on your computer; the tool list appears in your AI app after you install it.
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 publisher (blazingvideo.com) is not the repo owner (acstener); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 0 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 on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 11 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
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.
Record your screen, face and voice on your Mac, edit the video by its transcript, and share a link, all from Claude Code.
/plugin marketplace add acstener/blazing-video-plugin
/plugin install blazing-video@blazing-video
The plugin adds two things:
http://127.0.0.1:43120/mcp (header X-Takes: 1). It only answers on your Mac and refuses browser requests. If Claude says it can't connect, open Blazing Video.Without the plugin you can add the server yourself:
claude mcp add --transport http --scope user blazing-video http://127.0.0.1:43120/mcp --header "X-Takes: 1"
Using the Claude desktop app instead? Choose Connect to Claude App… in Blazing Video's menu-bar menu; it downloads a connector for the Claude app with the same tools.
| Tool | What it does |
|---|---|
start_recording | Starts recording the screen, camera and mic. Returns once it's rolling. Options: camera, microphone, systemAudio. If the camera can't start, it returns a warning and does not record; call again with camera: false. |
wait_for_take | Waits until the take stops (⌥⇧R, the island's Stop button, or stop_recording) and returns it with its transcript and share link, opened in the editor. Options: take, timeoutSeconds (default 900, max 3600). |
stop_recording | Stops the recording and returns the take and its transcript, opened in the editor. |
recording_status | Idle, starting, ready or recording; how long it's been rolling; the last finished take. |
| Tool | What it does |
|---|---|
understand_video | Reads a whole video in one call: duration, resolution, a timestamped transcript and up to 12 key frames (maxFrames 0–30, frameWidth 320–1568). Takes any .mp4/.mov/.m4v (or audio file) by path, or the open take with no path. Imports the file as a take and opens it, so the editing tools work on it next. Nothing is uploaded. |
open_take | Opens a take, or any video file (imported and transcribed on the Mac first), in the editor. With no path, opens the newest take. |
add_clip | Adds another take or video to the end of the open take, or at atMs (optionally just part of it, with inMs / durationMs). The words carry on in one transcript. remove takes a clip back out. |
| Tool | What it does |
|---|---|
get_transcript | Every word with its index, text, start/end time and whether it's cut, plus the current cuts, trim and durations. |
cut_ranges | Cuts words by index (wordIndices) or time ranges in ms (ranges). restore: true brings them back. |
cut_fillers | Cuts every um/uh-style filler word. |
tighten_pauses | Shortens every pause over 0.4 s down to 0.15 s. |
trim | Trims the start and/or end: startWord / endWord (first / last word to keep) or startMs / endMs. clear: true removes the trim. |
set_camera | Places and styles the webcam: corner or x/y, size, shape (circle, rounded, square), aspect (1:1, 4:3, 3:4, 16:9), zoom and panX/panY, visible, removeBackground, reset. |
set_captions | Animated burned-in captions timed to every kept word: style (clean, subtitles, bold-pop, beast, karaoke, word-box, one-word, marker, typewriter, keynote, serif), customStyle (any look field), words (per-word emphasis / color by transcript index), position / x / y, size, lineLength, textColor, highlightColor, box, enabled. |
save_subtitles | An .srt or .vtt of the edit, timed to the edited video. |
set_background | The studio look: the screen on a gradient wallpaper (dusk, ocean, aurora, mint, peach, snow, graphite) with padding, roundness and shadow. enabled: false goes back to full-frame. |
get_frame | A PNG of the edited video at timeMs (after cuts), webcam included. maxWidth defaults to 1280. |
undo | Undoes the last edit. Every edit above is one undo step. |
| Tool | What it does |
|---|---|
export | Writes an MP4 to ~/Movies/Blazing Video and returns the path. Options: codec (hevc default, or h264 for compatibility), height, fps (30 or 60). |
share | Returns a share link at once and copies it to the clipboard; the video uploads behind it. Sharing the same take again updates the same link. wait: true returns only once the link plays. Links are public (but unguessable), so only share when asked. |
cut_fillers, tighten_pauses, share.get_transcript, then trim and cut_ranges.set_camera, set_background, then get_frame to check.understand_video with the path.Recording, transcription and editing all happen on your Mac. Only share uploads anything.