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)
Control Tidbyt/Tronbyt LED displays: push text, images, and apps; brightness and night mode.
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.
TRONBYT_BASE_URL, TRONBYT_API_KEYValues 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 …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"tronbyt": {
"command": "npx",
"args": [
"-y",
"tronbyt-mcp"
],
"env": {
"TRONBYT_BASE_URL": "your-value",
"TRONBYT_API_KEY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add tronbyt --env TRONBYT_BASE_URL=your-value --env TRONBYT_API_KEY=your-value -- npx -y tronbyt-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"tronbyt": {
"command": "npx",
"args": [
"-y",
"tronbyt-mcp"
],
"env": {
"TRONBYT_BASE_URL": "your-value",
"TRONBYT_API_KEY": "your-value"
}
}
}
}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": {
"tronbyt": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tronbyt-mcp"
],
"env": {
"TRONBYT_BASE_URL": "your-value",
"TRONBYT_API_KEY": "your-value"
}
}
}
}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 registry name was verified with the GitHub account jonfishr, which owns the repo
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 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.
You need to fill in: TRONBYT_BASE_URL, TRONBYT_API_KEY
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 (0.1.0) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js 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.
Let your AI assistant put things on your LED sign.
If you have a Tidbyt or Tidbyt-style LED matrix display managed by a self-hosted tronbyt/server, this connects it to Claude (or any other AI tool that speaks MCP, the open standard for giving assistants access to tools). Once installed, your display becomes something you can just talk to your assistant about:
"Put BREAD'S DONE on the sign in amber."
"Dim the display to 20% and turn on night mode from 10pm to 7am."
"What apps are on the sign right now? Disable the stock ticker."
"Show the clock app for a bit."
The assistant handles the rest — rendering text into the display's pixel format, talking to your server, managing the app rotation. Everything runs on your own machine against your own server; nothing goes through any cloud service.
tronbyt-mcp is a small MCP server that wraps tronbyt/server's documented REST API. Your MCP client (Claude Code, Claude Desktop, and friends) launches it locally and talks to it over stdio; it talks to your Tronbyt server over HTTP with a device API key.
In the Tronbyt web UI, open your device's settings and copy (or generate) its API key. Keys are scoped to a single device — one key, one display.
Claude Code (one command):
claude mcp add tronbyt \
-e TRONBYT_BASE_URL=http://tronbyt.local:8000 \ -e TRONBYT_API_KEY= \ -- npx -y tronbyt-mcp
Claude Desktop: edit the config file — macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json — and add:
{
"mcpServers": { "tronbyt": { "command": "npx", "args": ["-y", "tronbyt-mcp"], "env": { "TRONBYT_BASE_URL": "http://tronbyt.local:8000", "TRONBYT_API_KEY": " " } } } }
Then restart Claude Desktop.
Any other MCP client: configure a stdio server with command npx, args ["-y", "tronbyt-mcp"], and the two environment variables above.
From source (instead of npx):
git clone https://github.com/jonfishr/tronbyt-mcp.git
cd tronbyt-mcp npm install && npm run build
Then use node /path/to/tronbyt-mcp/dist/index.js as the server command in your MCP client config (same environment variables).
Multiple displays? API keys are per-device, so add one entry per display (tronbyt-kitchen, tronbyt-office, …), each with its own key.
Ask your assistant something like *"List my Tronbyt devices."* You should get back your display with its brightness, night mode, and app list. (In Claude Code, /mcp also shows the server and its tools.)
| Env var | Required | Default | Notes |
|---|---|---|---|
TRONBYT_BASE_URL | yes | — | Your tronbyt/server, e.g. http://tronbyt.local:8000 |
TRONBYT_API_KEY | yes | — | Per-device API key from the Tronbyt web UI |
TRONBYT_TIMEOUT_MS | no | 10000 | Per-request timeout |
You don't call these directly — your assistant picks the right tool from your request — but this is what it has to work with:
| Tool | What it does |
|---|---|
list_devices | Devices visible to the key: brightness, night mode, pinned app, last seen |
update_device | Set brightness, rotation interval, night/dim mode, pinned app |
reboot_device | Reboot the display |
list_installations | Apps installed on the device, with state and config |
update_installation | Enable/disable, pin/unpin, or retime an installation |
delete_installation | Remove an installation and its rendered images |
push_app | Render a server-side app (with optional config) and show it |
push_image | Push a base64 WebP (64×32, or 128×64 for wide displays) straight to the display |
push_text | Render text to a display-sized WebP locally and push it |
Push tools take background: false (default) interrupts the display and shows the push immediately; true saves it into the rotation without interrupting. When a key sees exactly one device (the normal case), device_id never needs to be specified.
push_textText is rendered with the Tom Thumb 3×5 pixel font, word-wrapped and centered. Printable ASCII only; \n forces a line break. Colors are hex (#ffcc00), default white on black.
Canvas size is detected from the device type (size: "auto"): standard displays get 64×32, wide/2x displays (tronbyt_s3_wide, raspberrypi_wide) get 128×64. On wide displays the font is doubled by default — same 16 chars × 5 lines, twice the pixels. Pass text_size: "small" for native-size glyphs (32 chars × 10 lines), or override the detection entirely with size: "64x32" / "128x64".
claude mcp remove tronbyt"tronbyt" entry from the config file and restart the client.npx, a cached copy may linger under ~/.npm/_npx; it's small and harmless, or clear it with npm cache clean --force.npm install
npm test # vitest: unit + in-process MCP + stdio e2e (builds first) npm run build # tsc -> dist/ npm run gen:font # regenerate src/font.ts from scripts/tom-thumb.bdf
Smoke test against a real server (non-destructive — pushes to the rotation in background mode, then deletes the installation). Run from the repo root after a build:
TRONBYT_BASE_URL=http://tronbyt.local:8000 TRONBYT_API_KEY=<key> scripts/smoke.sh
update_firmware_settings — deliberately excluded; a bad value can leave a display unreachableMIT. The bundled pixel font is Tom Thumb / "Fixed4x6" by Brian J. Swetland and Robey Pointer (MIT), vendored as scripts/tom-thumb.bdf. This project is not affiliated with Tidbyt (the company) or the Tronbyt project.