Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
作者提供的说明(英文原文)
Pictures, video, voice and transcripts from any Vercel AI Gateway model, on your own Vercel copy.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://{host}/mcp/{secret}地址中有只有你知道的 {…} 部分(例如你的账户),请复制后自行填写。
在终端中运行这条命令
claude mcp add --transport http ai-gateway 'https://{host}/mcp/{secret}'地址中有只有你知道的 {…} 部分(例如你的账户),请复制后自行填写。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"ai-gateway": {
"url": "https://{host}/mcp/{secret}"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
地址中有只有你知道的 {…} 部分(例如你的账户),请复制后自行填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"ai-gateway": {
"type": "http",
"url": "https://{host}/mcp/{secret}"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://{host}/mcp/{secret}地址中有只有你知道的 {…} 部分(例如你的账户),请复制后自行填写。
菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
这个地址需要填入你自己的值,所以我们无法替你读取工具列表。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 Armulee 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
这个地址需要填入你自己的账户信息,所以我们无法替你检查
这个地址需要填入你自己的账户信息,所以我们无法替你检查
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(0.1.0)于23天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Figma Context MCP, Claude Real Video, Figma MCP Server
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
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.
The Figma MCP server brings Figma design context directly into your AI workflow.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
One click, and you are done.
Vercel copies this repo to your account, makes your private storage and asks for one secret. Your copy then walks you through the rest.
What you can make · How it works · Get started · What it costs · Tools · Keep it safe
The provider's own price, right inside your chat. No markup, no subscription, no API key. Add this connector to Claude, ChatGPT or any MCP app and it can make pictures, video and voice with 400+ models on Vercel AI Gateway: Veo, Kling, Seedance, Nano Banana, GPT Image, FLUX and more. You run your own copy on your own Vercel account, so every call is paid from your own Gateway credits at the price the provider sets.
A real chat on claude.ai, October 2026: a picture for $0.007, then a five-second video for $0.09 (HeyGen Video 1). Waiting while models work is sped up. See the demo .
Ask in plain words. Your chat does the thinking and the writing with everything it already knows about you; the connector makes the pictures, the video and the voice.
Shoot a short film "Write a one-minute sci-fi short, storyboard it, then film every scene with sound." Your chat writes the script and plans each shot. The connector draws the storyboard and films the scenes. generate_image start_video get_video
10 scenes with sound: $12.00 on Veo 3.1 Fast
Write and illustrate a book "Write a 12-chapter bedtime story about a fox who collects stars, and paint every chapter in watercolour." Your chat writes the story. The connector paints the cover and a picture for each chapter, in one style. generate_image edit_image
12 pictures: $1.61 on Nano Banana Pro
Turn it into an audiobook "Read chapter one aloud in a warm, slow voice, like a bedtime story." The connector narrates the text and hands back an audio file you can play right in the chat. generate_speech
A 2,000-word chapter: about $0.33 on TTS-1 HD
Shoot a product "Take this photo of my mug, put it on white marble in morning light, then make a slow turntable clip." The connector edits your own photo into new shots, then films a short clip from the best one. edit_image start_video get_video
4 shots and a 5-second clip: $0.66 on FLUX Kontext Pro and Veo 3.1 Fast
Make anyone dance "Make the character in this picture do the dance in this video." The connector copies the moves from a reference video onto your character, frame by frame. motion_control get_video
A 10-second dance: $1.26 on Kling 3.0 Motion Control
Run a month of posts "Plan 30 days of posts for my bakery, write the captions, and make a picture for each day." Your chat plans the month. The connector makes a picture for every day and vertical clips for the big ones. generate_image start_video get_video
30 pictures and 8 clips: $10.43 on Nano Banana Pro and Veo 3.1 Fast
Turn a recording into notes "Transcribe this meeting with timestamps, then give me the decisions and who owns what." The connector writes down every word; your chat turns it into notes, subtitles or a translation. transcribe
A 20-minute recording: $0.12 on Whisper
Pick the right model "Which video model is cheapest for an 8-second clip that still looks good?" The connector lists every model with its AI Gateway catalog price, so your chat can choose for you, or compare a few side by side. list_models check_credits
Free reading the catalog costs nothing
Costs are AI Gateway catalog prices from October 2026, for the example quantities shown. They are examples, not quotes: the provider's bill can differ from the catalog (see What it costs ), and each call reports what it actually cost. Ask list_models for today's catalog.
What is MCP? The Model Context Protocol is how chat apps plug in outside tools. This project is one of those tools: once you add its link, your chat app can make things with any model on AI Gateway.
You need a Vercel account and a GitHub, GitLab or Bitbucket account.
Then set a spend budget in the Vercel dashboard (AI Gateway → Budgets). It is the real limit on what your link can ever spend.
Open your copy and it shows where you are: an arch of six stones, one per step. Set stones glow, the next one breathes, and clicking a stone opens its step.
One step at a time. Done steps fold away and the next one opens with exactly what to do.
Your link, tested. In the browser that made your secret it's checked by itself; anywhere else, paste it once and test it. Open on your phone shows a QR code that opens your page on your phone with the secret already saved. Claude on your phone needs none of this: connectors added on claude.ai show up there by themselves.
A secret that never leaves your browser. Made and saved there the moment you reach the step, with your link ready to copy. Vercel only gets its fingerprint ( MCP_SECRET_SHA256 ), which can't open your connector: add it, redeploy once (it covers the storage too), and the page checks your link by itself. Or press Copy setup prompt and paste it into Claude with the Vercel connector: it adds the fingerprint and redeploys for you.
Into your chat app. Steps for Claude, ChatGPT and any other MCP app, and a test prompt to try it.
Once every step is done, the guide steps aside for good. From then on your page opens on the brand and goes straight to your usage. If anything comes undone later (say MCP_SECRET_SHA256 is removed), the guide comes back by itself.
<img src="docs/readme/intro.webp" width="100%" alt="With setup done: a point of light, the arch built outward from it, the arch shrinking into the logo as the name appears, then flying to the corner as the us
只显示了开头部分;其余内容请在仓库中阅读