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)
Vietnamese-first text to speech, photo tools, Word to PDF and TCVN3/VNI fixes. Free daily allowance.
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://yangopen.com/mcpRun this in your terminal
claude mcp add --transport http yangopen https://yangopen.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"yangopen": {
"url": "https://yangopen.com/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": {
"yangopen": {
"type": "http",
"url": "https://yangopen.com/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://yangopen.com/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.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
list_voicesThe YangOpen voices. tier "free" (default): sixteen free voices — two Vietnamese (Southern accent), American and British English, Mandarin, Japanese, Korean, Thai, French and Spanish. tier "plus": the paid voices, about 2,600 — 182 Vietnamese (Northern, Central and Southern), Eng
text_to_speechTurn text into speech with a free YangOpen voice and get a link to the MP3. It costs no credit; it counts against the user's free daily allowance. Up to 3,000 characters per call: split longer text at sentence ends and call once per part. The link works for 24 hours; give it to t
text_to_speech_plusTurn text into speech with a Plus voice and get a link to the MP3. Spends the user's prepaid YangOpen credit: 25 credits per 1,000 characters, rounded up to whole credits. The charge is made only when the MP3 is ready, and the answer states what was charged and the balance left.
get_balanceThe user's YangOpen credit balance, what it buys (Plus voice characters, paid image runs), the prices, and where to top up. Changes nothing.
get_upload_linkA one-time page where the user uploads a file for the tools that need one: a photo (JPEG, PNG or WebP) for the image tools and scan_document, or a Word, Excel or PowerPoint file for word_to_pdf, excel_to_pdf or powerpoint_to_pdf, up to 25 MB. It gives the file_id to pass to them.
remove_backgroundCut the main subject out of a photo and get a PNG with a transparent background. 5 free runs a day for each image tool, then 25 credits a run, charged only when the result is ready. Give the photo as file_id (the user uploads it through get_upload_link) or image_url. The result l
colorize_photoColour a black-and-white or toned (sepia) photo, with faces restored. A photo that already has colour comes back as it was and costs nothing. 5 free runs a day for each image tool, then 25 credits a run, charged only when the result is ready. Give the photo as file_id (the user u
sharpen_imageMake a blurry, small or old photo sharp and larger (AI upscaling). It can also restore faces, and clean scratches and dust from an old print. 5 free runs a day for each image tool, then 25 credits a run, charged only when the result is ready. Give the photo as file_id (the user u
expand_imageExtend a photo with AI-painted surroundings: to a new shape such as 16:9 (a cover), 9:16 (a phone story) or 1:1, or by a share of its size on the sides you choose. It never crops: the original pixels stay as they were. Can take up to a minute. 5 free runs a day for each image too
scan_documentTurn a phone photo of a page (a document, a receipt, a page of a book) into a flat, straight scan: the page is found, cut out of the background and unbent, and comes back as a JPEG. 5 free runs a day for each image tool, then 25 credits a run, charged only when the result is read
word_to_pdfTurn a Word document (.docx or .doc, up to 25 MB) into a PDF with the layout Word gave it, on YangOpen's server. A few hundred pages take under half a minute; a much longer document may not finish. 5 free files a day, then 25 credits a file, charged only when the PDF is ready. Gi
excel_to_pdfTurn an Excel workbook (.xlsx or .xls, up to 25 MB) into a PDF on YangOpen's server, with each sheet on one page so a wide sheet is not cut. 5 free files a day, then 25 credits a file, charged only when the PDF is ready. Give the file as file_id (the user uploads it through get_u
powerpoint_to_pdfTurn a PowerPoint presentation (.pptx or .ppt, up to 25 MB) into a PDF on YangOpen's server, one slide a page. 5 free files a day, then 25 credits a file, charged only when the PDF is ready. Give the file as file_id (the user uploads it through get_upload_link) or file_url. The P
convert_vietnamese_fontTurn Vietnamese text typed in the old fonts (TCVN3/ABC such as .VnTime, or VNI such as VNI-Times) into Unicode, so it reads right in any font: "Céng hßa x· héi chñ nghÜa" becomes "Cộng hòa xã hội chủ nghĩa". The old font is guessed from the text unless you name it. Up to 5,000 ch
convert_timeWhat a time in one place is in other places, with daylight saving applied for that date. Name zones the IANA way (Asia/Ho_Chi_Minh, America/New_York, Europe/London, Australia/Sydney) or UTC. Free.
number_to_wordsWrite a number in Vietnamese and English words, for an invoice or a receipt: 1.250.000 becomes "một triệu hai trăm năm mươi nghìn" and "one million two hundred fifty thousand". A dot or comma before exactly three digits groups thousands (1.250, 12,500); before other digits it is
count_textCount a text the way a writer does: words, characters with and without spaces, sentences, paragraphs, lines, and reading and speaking time. Vietnamese syllables count as words (the way Word counts them); a word is a run of letters and digits between spaces, so "e-mail", "COVID-19
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 9, 2026
The registry lists no source repo, so we cannot match the publisher (yangopen.com) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 131 ms (HTTP 200)
No sign-in needed
Read 17 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 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.
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 (1.4.0) reached the registry 14 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.
No README found in the repo