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)
Local PDF, Office, image, archive and video tools for AI agents. Files never leave your computer.
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。
ROUNDERTOOLS_ALLOW, ROUNDERTOOLS_FFMPEG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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"roundertools": {
"command": "npx",
"args": [
"-y",
"@roundertools/mcp"
],
"env": {
"ROUNDERTOOLS_ALLOW": "your-value",
"ROUNDERTOOLS_FFMPEG": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add roundertools --env ROUNDERTOOLS_ALLOW=your-value --env ROUNDERTOOLS_FFMPEG=your-value -- npx -y @roundertools/mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"roundertools": {
"command": "npx",
"args": [
"-y",
"@roundertools/mcp"
],
"env": {
"ROUNDERTOOLS_ALLOW": "your-value",
"ROUNDERTOOLS_FFMPEG": "your-value"
}
}
}
}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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"roundertools": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@roundertools/mcp"
],
"env": {
"ROUNDERTOOLS_ALLOW": "your-value",
"ROUNDERTOOLS_FFMPEG": "your-value"
}
}
}
}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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
ROUNDERTOOLS_ALLOW envROUNDERTOOLS_FFMPEG env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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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7日
注册名称已通过 GitHub 账户 adam-sari 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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.3.0)于3天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
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:★ 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。
An MCP server that gives AI assistants the file tools from roundertools.com: compress, merge, split and protect PDFs, convert and resize images, zip files, and (with ffmpeg) shrink, convert and trim video. It runs on your computer over stdio. Files stay where they are, and it makes no network requests.
Claude Code:
claude mcp add roundertools -- npx -y @roundertools/mcp
claude mcp add roundertools --scope user -- npx -y @roundertools/mcp --allow ~/Documents --allow ~/Downloads
In Claude Code you may not need a server at all. The roundertools plugin (/plugin marketplace add adam-sari/rounder, then /plugin install roundertools@roundertools) is a skill that teaches Claude to run the CLI, about 100 tokens until it's used.
Claude Desktop (claude_desktop_config.json, under Settings → Developer → Edit config):
{ "mcpServers": { "roundertools": { "command": "npx", "args": ["-y", "@roundertools/mcp", "--allow", "/Users/you/Documents"] } } }
On Windows, if npx isn't found, use "command": "cmd", "args": ["/c", "npx", "-y", "@roundertools/mcp", …].
Cursor (~/.cursor/mcp.json or .cursor/mcp.json):
{ "mcpServers": { "roundertools": { "command": "npx", "args": ["-y", "@roundertools/mcp"] } } }
VS Code (.vscode/mcp.json):
{ "servers": { "roundertools": { "type": "stdio", "command": "npx", "args": ["-y", "@roundertools/mcp"] } } }
Needs Node 22.13 or newer; video and audio tools appear when ffmpeg is on the PATH (or at ROUNDERTOOLS_FFMPEG).
--allow DIR (repeatable) or ROUNDERTOOLS_ALLOW (a path list). Without either: your home folder and the folder it starts in (when that's a project, not a system folder). A client's roots can narrow this, never widen it..ssh, .aws, .config, .env…), key and password files, or app data such as browser profiles, even inside an allowed folder. Paths must be absolute; symlinks are resolved before checking. The one exception is the server's own settings folder, which it reads at startup; no tool call can.--out DIR. It never replaces an existing file and never writes over an input. The one other place it writes is its own settings folder.-protocol_whitelist file,pipe).\\server\share.Text and details read out of files (document-to-markdown, pdf-to-text, form fields, a PDF's title, EXIF fields) come back framed as the file's content, not instructions, between tags with a random name the file can't guess.
A client sends every tool a server lists to the model at the start of every conversation, used or not. Listing every tool up front (38 with ffmpeg) costs about 18,000 tokens. So by default the server lists three helpers, about 700 tokens, plus a short paragraph of instructions (about 150):
find-tool: searches every tool on the site by what you want donedescribe-tool: any tool's options as JSON Schemarun-tool: runs any tool that works outside a browser, with the same checksBehind them are merge-pdf, split-pdf, compress-pdf, protect-pdf, unlock-pdf, organize-pdf, add-page-numbers-to-pdf, watermark-pdf, jpg-to-pdf, pdf-to-text, extract-images-from-pdf, pdf-form-fields, fill-pdf-form, with @napi-rs/canvas pdf-to-jpg and redact-pdf, then image-converter, image-compressor, image-resizer, crop-image, rotate-image, exif-remover, image-prep, image-diff, zip-files, unzip-files, checksum-calculator, file-info, document-to-markdown, spreadsheet-inspector, and with ffmpeg video-compressor, video-converter, trim-video, mute-video, video-to-gif, video-to-mp3, audio-converter, video-contact-sheet, plus the site's other tools that run outside a browser.
The list grows with use:
describe-tool, or runs one successfully with run-tool, the server lists that tool directly and tells the client (notifications/tools/list_changed), so next time it can call it by name. find-tool only searches, and a failed run adds nothing. A client that ignores list changes still reaches every tool through run-tool, which is what find-tool and the prompts name for any tool not listed from the start. Each change to the list can make a client re-read it (and lose a cached prompt), so it happens once per tool.--tools all lists every tool up front, if you'd rather pay the tokens once than have the assistant search. --tools default lists the set 0.1 listed by default (everything but checksum-calculator). Families (--tools pdf,image) and tool names (--tools compress-pdf,merge-pdf) list just those. They all combine: --tools lean,pdf or --tools default,checksum-calculator. The helpers are always there. The flag wins over the settings file, and the settings file wins over the lean default.
Each tool takes inputs (absolute paths), an optional output (a folder, or a new file for a single result) and its own options. Results come back as a summary, resource_links to the files, and structuredContent with each output's path, size and type. Image tools take preview: true for a small PNG of the result.
In a terminal coding agent (Claude Code, Codex, Gemini CLI, opencode), the first find-tool result says once that npx -y roundertools … does the same without MCP. Nothing else depends on which client is connected.
Prompts cost nothing until you pick one. Each tells the assistant which tool to call, with which arguments.
| Prompt | Arguments |
|---|---|
compress-pdf | file, optional size (like 1mb) |
merge-pdfs | files |
convert-images | files, format |
pdf-to-text | file |
read-document | file (PDF, Word, PowerPoint, Excel or CSV) |
fill-pdf-form | file (lists the fields, asks you, then fills) |
redact-pdf | file, what (only with @napi-rs/canvas) |
shrink-video | file, optional size (only with ffmpeg) |
Favourites come from a count of the tools you use. After a tool runs successfully, the server adds one to its count and notes the date in usage.json:
{ "version": 1, "tools": { "compress-pdf": { "count": 4, "last": "2026-11-02" } } }
That's all it stores: tool names, counts and dates. Never paths, file names, options or anything read from a file. It stays on your computer like everything else.
Turn it off with --no-memory, ROUNDERTOOLS_MEMORY=off, or npx roundertools config set memory off. Forget it all with npx roundertools config reset.
settings.json and usage.json live in one folder:
| System | Folder |
|---|---|
| Windows | %APPDATA%\roundertools |
| macOS | ~/Library/Application Support/roundertools |
| Linux and others | $XDG_CONFIG_HOME/roundertools, or ~/.config/roundertools |
ROUNDERTOOLS_CONFIG_DIR picks another folder. The CLI shows and changes them:
npx roundertools config # the folder, the settings and your favourites
npx roundertools config set tools all # lean, all, default, families or tool names npx roundertools config set memory off # on or off npx roundertools config reset # remove both files
A change applies the next time the server starts, and flags on its command line win. On Node 26 and newer the permission model gives the server read and write access to this folder, so memory keeps working there too. With memory off it may only read it.
| Option | |
|---|---|
--allow DIR | a folder it may read (repeatable) |
--out DIR | a folder it may write to, besides next to the inputs |
--tools LIST | lean (the default), all, default, families (pdf,image,files,media) or tool names |
--no-memory | don't count which tools you use |
--experimental | turn on features that aren't finished (there are none yet) |
--max-input SIZE | per-file limit (default 1gb, media 2gb) |
--timeout MIN | minutes per call (default 5, media 30) |
--max-outputs N | files one call may write (default 500) |
Built on the official MCP TypeScript SDK (@modelcontextprotocol/server), stdio only; it logs to stderr, runs one heavy job at a time, sends progress notifications and stops when a call is cancelled.
MIT. Docs: roundertools.com/developers/mcp. Source: github.com/adam-sari/rounder in packages/mcp.