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)
45+ interactive charts, dashboards, flowcharts, and KPIs inside any AI conversation
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"dashboards": {
"command": "npx",
"args": [
"-y",
"mcp-dashboards"
]
}
}
}在终端中运行这条命令
claude mcp add dashboards -- npx -y mcp-dashboards粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"dashboards": {
"command": "npx",
"args": [
"-y",
"mcp-dashboards"
]
}
}
}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": {
"dashboards": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-dashboards"
]
}
}
}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。
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8日
注册名称已通过 GitHub 账户 KyuRish 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(2.4.0)于4个月前进入注册中心。
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:↓ 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。
Click any thumbnail to see full size
We use AI for everything - analysis, reports, strategy. But when it comes to actually *seeing* the story in your data, you're stuck copying numbers into a spreadsheet and building charts yourself. The conversation has the insight. The visualization is somewhere else.
MCP Dashboards renders interactive charts, dashboards, and KPI widgets directly inside your AI conversation. 32 chart tools covering 45+ chart subtypes (bar has stacked/drilldown, hero has 11 variants, flowchart has 6 node kinds + 5 edge styles, etc.), 21 themes, 4 visual discovery catalogs, live polling, PNG/PPT/A4 export - all from a single MCP server. No browser tabs, no copy-paste, no context switching.
| Client | Interactive in-chat rendering | How |
|---|---|---|
| Claude Desktop | Yes (MCP Apps) | stdio config below |
| claude.ai (web) | Yes (MCP Apps) | remote connector |
| ChatGPT | Yes (MCP Apps) | remote server via Developer mode (Settings → Apps → Advanced) |
| VS Code GitHub Copilot | Yes (MCP Apps) | stdio config |
| Goose / Postman / MCPJam | Yes (MCP Apps) | stdio or remote |
| Claude Code (CLI) | Tools + browser preview fallback | claude mcp add below; charts open in a local browser tab |
ChatGPT and claude.ai need a remotely hosted endpoint (Streamable HTTP mode below); the desktop clients spawn the server locally.
[!IMPORTANT]
The only official npm package is
mcp-dashboards, published from this repository. Similarly named packages are not ours:mcp-dashboards-sharedwas malware (see OSSF advisory MAL-2026-4296, removed by npm security in May 2026). Install onlymcp-dashboards.
Add to your claude_desktop_config.json:
%APPDATA%\Claude\claude_desktop_config.json~/Library/Application Support/Claude/claude_desktop_config.json{
"mcpServers": { "dashboard": { "command": "npx", "args": ["-y", "mcp-dashboards", "--stdio"] } } }
claude mcp add dashboard -- npx -y mcp-dashboards --stdio
npx mcp-dashboards
Bound to localhost by default. See Configuration if you need to expose it on your network or allow browser access from a non-localhost origin.
Works in any MCP Apps-compatible client: Claude Desktop, Claude Web, VS Code (GitHub Copilot), Goose, Postman, MCPJam. ChatGPT support is rolling out.
No API to learn. Describe what you want in plain English:
The AI picks the right tool, formats your data, and renders the chart inline. Click any data point to ask follow-up questions.
Don't know where to start? Ask *"show me the catalog"* - opens a master dashboard with one live visual tile per customization dimension (a real bar chart for charts, a pie for themes, a progress ring for hero variants, a neon-glowing card for effects). Click any tile, hit Ask, and you'll drill into that sub-catalog.
Every chart is interactive HTML rendered directly in your conversation:
All Tools
| Tool | Type | Best For |
|---|---|---|
render_pie_chart | Pie/Donut | Composition - "what makes up the whole?" |
render_bar_chart | Bar | Comparison - vertical, horizontal, stacked, drill-down |
render_line_chart | Line/Area | Trends - smooth curves, gradient fills, time series |
render_scatter_chart | Scatter | Relationships - per-point labels, annotations, quadrants |
render_candlestick_chart | Candlestick | Finance - OHLC data with volume bars |
render_radar_chart | Radar | Multi-axis comparison - skills, scores, product attributes |
render_treemap_chart | Treemap | Hierarchy - nested rectangles sized by value |
render_sankey_chart | Sankey | Flow - money, users, or resources between stages |
render_wordcloud_chart | Word Cloud | Frequency - sized words from text analysis |
render_boxplot_chart | Boxplot/Violin | Distribution - quartiles, outliers, density shapes |
render_live_chart | Live | Real-time - auto-polls any MCP tool on a timer |
poll_http | Data proxy | Fetch JSON from any HTTP endpoint - secure presets or public URLs |
render_bullet_chart | Bullet | KPI vs target - 2-8 zone bands with labels |
render_lollipop_chart | Lollipop | Ranking - clean dots with optional target markers |
render_dumbbell_chart | Dumbbell | Gaps - before/after with scale labels and zone bands |
render_variance_chart | Variance | Budget - actual vs budget, color-coded over/under |
render_funnel_chart | Funnel | Conversion - staged drop-off with percentages |
render_slope_chart | Slope | Change - ranking shifts between two periods |
render_waffle_chart | Waffle | Proportion - 10x10 grid showing composition |
render_sparkline_chart | Sparkline | Compact trends - mini cards with change indicators |
render_radial_cluster | Radial | Health check - multi-metric ring gauges with status |
render_waterfall_chart | Waterfall | Cumulative - cascading bars showing impact |
render_heatmap_chart | Heatmap | Intensity - 2D grid with color mapping |
render_geo_chart | Geo/Map | Geography - color-coded countries by value (choropleth) |
render_bubble_map | Bubble Map | Pin map - sized circles at lat/lng coordinates |
render_timeline_chart | Timeline | Progress - milestone tracker with status indicators |
render_flowchart | Flowchart | Workflows, pipelines, architectures, agent flows - rich card-based DAG with status states, drag, zoom, live polling |
render_hero_metric | Hero | KPI widgets - 11 variants (progress ring, gem, orb, NPS, etc.) |
render_dashboard | Dashboard | Everything - KPI cards + multiple charts in responsive grid |
render_table | Table | Data - sortable columns, striped rows, CSV export |
render_from_json | Auto-detect | Any JSON data - picks the best chart automatically |
render_from_url | URL fetch | Fetches JSON from a URL and auto-visualizes |
Discovery / Catalogs - visual entry points for browsing what's available:
| Tool | Shows | When to use |
|---|---|---|
render_catalog | Master catalog with 4 live preview tiles | Don't know where to start. Click any tile, hit Ask, drill in. |
render_chart_catalog | All 32 chart types with mini previews | Looking for the right chart for your data |
render_theme_catalog | All 21 themes with color/typography/effects | Picking a theme |
render_hero_catalog | All 11 hero metric variants | Picking a KPI widget style |
render_effects_catalog | All 5 effect presets, each applied to a real card | Picking an animation/glow style |
Typography is still configurable on every chart via typography= (8 options listed under Themes) - it just doesn't have its own catalog because all 8 options were visually identical without per-card font loading, which wasn't worth the build for one preview tool.
Which chart should I use?
| Question | Best Chart | Also Works |
|---|---|---|
| "What makes up the whole?" | Pie/Waffle | Treemap, Stacked bar |
| "How do values compare?" | Bar | Lollipop, Bullet, Radar |
| "What's the trend over time?" | Line | Sparkline, Slope |
| "Are we hitting targets?" | Bullet | Variance, Radial |
| "Where's the gap?" | Dumbbell | Variance |
| "How does X relate to Y?" | Scatter | Heatmap |
| "What's the conversion rate?" | Funnel | Waterfall, Sankey |
| "What changed between periods?" | Slope | Dumbbell |
| "What's the financial picture?" | Candlestick | Line |
| "Show me the KPI" | Hero metric | Dashboard |
| "What's the distribution?" | Boxplot | Violin (same tool) |
| "Where does money/traffic flow?" | Sankey | Treemap |
| "How do options score across axes?" | Radar | Heatmap |
| "What are the top keywords?" | Word Cloud | Bar, Treemap |
| "Where are users/sales/revenue?" | Geo map | Bubble map, Heatmap |
| "Monitor this in real-time" | Live chart | - |
21 built-in themes. Pass theme to any tool.
| Family | Themes |
|---|---|
| Classic | boardroom, corporate, sales-floor, golden-treasury, clinical, startup, ops-control, tokyo-midnight, zen-garden, consultant |
| Black/AI | black-tron (cyan neon), black-elegance (warm gold), black-matrix (green hacker) |
| Forest | forest-amber (autumn), forest-earth (terracotta) |
| Sky | sky-light (airy blue), sky-ocean (deep navy), sky-twilight (sunset) |
| Office | office-red (corporate red, white bg - report-ready) |
| Gray/ML | gray-hf (warm yellow accent), gray-copilot (teal on dark) |
Mix-and-match with palette, typography (8 options: system, mono, professional, editorial, bold, techno, cyberpunk, luxury), and effects (5 presets: none, subtle, shimmer, neon, energetic).
Real-time charts that auto-update from any API. The live chart polls data via poll_http, which supports two modes:
只显示了开头部分;其余内容请在仓库中阅读