convez.ai
MCP ServerDados & AnalyticsIntermediário
KyuRish

MCP Dashboards

KyuRish/mcp-dashboards

Visualize dados interativos diretamente no seu chat com IA

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que transforma dados em dashboards interativos e gráficos visuais dentro de clientes IA como Claude. Oferece 31 ferramentas de visualização cobrindo 44+ subtipos de gráficos, 21 temas, exportação em PNG/PPT/PDF e atualização em tempo real, tudo sem sair da conversa.

Instalação

$npx convez-ai KyuRish/mcp-dashboards

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
54
Forks
11
Acompanhando
2
Saúde
42%
Último commit
há 2 meses
Versão
v2.4.1
Issues abertas
0
Contribuidores
1

Casos de uso

  • Criar dashboards executivos com KPIs em tempo real
  • Analisar comparações de dados com gráficos múltiplos
  • Acompanhar métricas financeiras e de vendas graficamente
  • Exportar relatórios visuais em PowerPoint e PDF

Veredito

Solução madura e bem-construída que elimina o atrito entre análise em IA e visualização. Diferencial real para quem trabalha com dados e precisa de insights visuais sem deixar o fluxo de conversa.

README

A tradução para o português deste README ainda está na fila.

MCP Dashboards

Your AI can talk about data. Now it can show it.

npm Glama Quality Glama Security License: FSL-1.1-MIT Buy Me A Coffee GitHub Sponsors

The problem

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.

The solution

MCP Dashboards renders interactive charts, dashboards, and KPI widgets directly inside your AI conversation. 31 tools covering 44+ chart subtypes (bar has stacked/drilldown, hero has 11 variants, etc.), 21 themes, live polling, PNG/PPT/A4 export - all from a single MCP server. No browser tabs, no copy-paste, no context switching.

Quick Start

Claude Desktop

Add to your claude_desktop_config.json:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "dashboard": {
      "command": "npx",
      "args": ["-y", "mcp-dashboards", "--stdio"]
    }
  }
}

Claude Code / VS Code

claude mcp add dashboard -- npx -y mcp-dashboards --stdio

Remote (Streamable HTTP)

npx mcp-dashboards
# Server starts on http://localhost:3001/mcp

Supported clients

Works in any MCP Apps-compatible client: Claude Desktop, Claude Web, VS Code (GitHub Copilot), Goose, Postman, MCPJam. ChatGPT support is rolling out.

Just ask

No API to learn. Describe what you want in plain English:

  • "Compare Q1 vs Q2 revenue by region as a bar chart"
  • "Show my portfolio allocation as a donut chart with the boardroom theme"
  • "Build a dashboard with monthly sales KPIs and a trend line"
  • "Visualize website traffic by country on a world map"
  • "Track Bitcoin price live, updating every 30 seconds"
  • "Show the conversion funnel from signup to purchase"
  • "Rank the team by performance using a radar chart"

The AI picks the right tool, formats your data, and renders the chart inline. Click any data point to ask follow-up questions.

Interactive charts, not images

Every chart is interactive HTML rendered directly in your conversation:

  • Explore in-chat - hover tooltips, click-to-select (feeds back to the AI), drill-down with breadcrumbs, scroll-zoom up to 12x on maps and heatmaps
  • Live polling - real-time charts that auto-update from any API on a timer
  • Export anywhere - PPT (16:9 slides), A4 (paginated with smart page breaks), PNG, CSV
ToolTypeBest For
render_pie_chartPie/DonutComposition - "what makes up the whole?"
render_bar_chartBarComparison - vertical, horizontal, stacked, drill-down
render_line_chartLine/AreaTrends - smooth curves, gradient fills, time series
render_scatter_chartScatterRelationships - per-point labels, annotations, quadrants
render_candlestick_chartCandlestickFinance - OHLC data with volume bars
render_radar_chartRadarMulti-axis comparison - skills, scores, product attributes
render_treemap_chartTreemapHierarchy - nested rectangles sized by value
render_sankey_chartSankeyFlow - money, users, or resources between stages
render_wordcloud_chartWord CloudFrequency - sized words from text analysis
render_boxplot_chartBoxplot/ViolinDistribution - quartiles, outliers, density shapes
render_live_chartLiveReal-time - auto-polls any MCP tool on a timer
poll_httpData proxyFetch JSON from any HTTP endpoint - secure presets or public URLs
render_bullet_chartBulletKPI vs target - 2-8 zone bands with labels
render_lollipop_chartLollipopRanking - clean dots with optional target markers
render_dumbbell_chartDumbbellGaps - before/after with scale labels and zone bands
render_variance_chartVarianceBudget - actual vs budget, color-coded over/under
render_funnel_chartFunnelConversion - staged drop-off with percentages
render_slope_chartSlopeChange - ranking shifts between two periods
render_waffle_chartWaffleProportion - 10x10 grid showing composition
render_sparkline_chartSparklineCompact trends - mini cards with change indicators
render_radial_clusterRadialHealth check - multi-metric ring gauges with status
render_waterfall_chartWaterfallCumulative - cascading bars showing impact
render_heatmap_chartHeatmapIntensity - 2D grid with color mapping
render_geo_chartGeo/MapGeography - color-coded countries by value (choropleth)
render_bubble_mapBubble MapPin map - sized circles at lat/lng coordinates
render_timeline_chartTimelineProgress - milestone tracker with status indicators
render_hero_metricHeroKPI widgets - 11 variants (progress ring, gem, orb, NPS, etc.)
render_dashboardDashboardEverything - KPI cards + multiple charts in responsive grid
render_tableTableData - sortable columns, striped rows, CSV export
render_from_jsonAuto-detectAny JSON data - picks the best chart automatically
render_from_urlURL fetchFetches JSON from a URL and auto-visualizes
QuestionBest ChartAlso Works
"What makes up the whole?"Pie/WaffleTreemap, Stacked bar
"How do values compare?"BarLollipop, Bullet, Radar
"What's the trend over time?"LineSparkline, Slope
"Are we hitting targets?"BulletVariance, Radial
"Where's the gap?"DumbbellVariance
"How does X relate to Y?"ScatterHeatmap
"What's the conversion rate?"FunnelWaterfall, Sankey
"What changed between periods?"SlopeDumbbell
"What's the financial picture?"CandlestickLine
"Show me the KPI"Hero metricDashboard
"What's the distribution?"BoxplotViolin (same tool)
"Where does money/traffic flow?"SankeyTreemap
"How do options score across axes?"RadarHeatmap
"What are the top keywords?"Word CloudBar, Treemap
"Where are users/sales/revenue?"Geo mapBubble map, Heatmap
"Monitor this in real-time"Live chart-

Themes

21 built-in themes. Pass theme to any tool.

FamilyThemes
Classicboardroom, corporate, sales-floor, golden-treasury, clinical, startup, ops-control, tokyo-midnight, zen-garden, consultant
Black/AIblack-tron (cyan neon), black-elegance (warm gold), black-matrix (green hacker)
Forestforest-amber (autumn), forest-earth (terracotta)
Skysky-light (airy blue), sky-ocean (deep navy), sky-twilight (sunset)
Officeoffice-red (corporate red, white bg - report-ready)
Gray/MLgray-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).

Live Polling

Real-time charts that auto-update from any API. The live chart polls data via poll_http, which supports two modes:

Secure presets (authenticated APIs)

Configure presets via env vars. Credentials stay server-side and never appear in the conversation.

{
  "mcpServers": {
    "dashboard": {
      "command": "npx",
      "args": ["-y", "mcp-dashboards", "--stdio"],
      "env": {
        "POLL_PRESET_T212_CASH_URL": "https://live.trading212.com/api/v0/equity/account/cash",
        "POLL_PRESET_T212_CASH_HEADERS": "{\"Authorization\": \"Bearer YOUR_API_KEY\"}"
      }
    }
  }
}

Then ask: "Monitor my portfolio total and P/L live" - the AI uses render_live_chart with pollArgs: { preset: "t212_cash" }.

Naming: POLL_PRESET_<NAME>_URL and POLL_PRESET_<NAME>_HEADERS (JSON object).

Public URLs (no auth needed)

For public APIs, use the URL directly:

"Show me Bitcoin price updating every 30 seconds" - uses pollArgs: { url: "https://api.coingecko.com/api/v3/simple/price?ids=bitcoin&vs_currencies=usd" }.

How It Works

Built on MCP Apps. You ask the AI to visualize data, it calls the right tool, and the chart renders inline in your conversation. Self-contained - zero CDN, zero external requests.

MCP Apps supported (inline rendering): Claude Desktop, VS Code Insiders + MCP Apps extension, Goose, Postman.

No MCP Apps support? No problem. When the server detects your client can't render inline, every chart response includes:

  • A clickable http://localhost:XXXX/chart/{id} link - opens the full interactive dashboard in your default browser
  • A standalone HTML file (file:///...chart-{id}.html) - self-contained, works offline, can be emailed or archived

Works in Claude Code, Cursor, older VS Code, and any other MCP client. Tool annotations (readOnlyHint, idempotentHint, openWorldHint) help clients reason about tool behavior.

Opt-out: set env var MCP_DASHBOARDS_DISABLE_PREVIEW=1 to skip the preview links entirely.

Requirements: Node.js 18+.

git clone https://github.com/KyuRish/mcp-dashboards.git
cd mcp-dashboards
npm install
npm run build
npm run serve   # http://localhost:3001
npm run dev     # watch mode

Support

If MCP Dashboards is useful to you:

Buy Me A Coffee GitHub Sponsors

Privacy

All processing happens locally. No data is collected, transmitted, or stored. External network calls are render_from_url and poll_http - both require you to explicitly provide the URL. Credentials in env var presets never leave your machine. The browser preview server binds only to 127.0.0.1 (localhost) and is not reachable from other devices.

License

FSL-1.1-MIT - Free to use for any purpose except building a competing commercial product. Each version converts to MIT two years after release. For commercial licensing, contact contact@kyuish.com.

Ver o original no GitHub

Bom para

Relacionados