Skip to main content
Glama

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 LinkedIn

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.

Related MCP server: trading212-mcp-server

The solution

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.

Works in

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 ismcp-dashboards, published from this repository. Similarly named packages are not ours: mcp-dashboards-shared was malware (see OSSF advisory MAL-2026-4296, removed by npm security in May 2026). Install only mcp-dashboards.

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://127.0.0.1:3001/mcp

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.

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"

  • "Diagram my multi-agent pipeline as a flowchart and let me step through it"

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.

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

  • Editable flowcharts - drag nodes, multi-select, rename via right-click, minimap + node list to navigate, step-through playback of the flow, then sync your layout back to the AI to save it

  • 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

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=<name> (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.

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

-

Themes

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).

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. Every chart response also includes a clickable link to the same interactive chart in your browser:

  • http://localhost:PORT/chart/{id} - the clickable link in chat. Backed by a tiny same-machine HTTP server bound to 127.0.0.1, lazy-started on the first preview request.

  • file:///.../chart-{id}.html - the persistent shareable artifact. Same HTML bytes, written to disk so you can email, archive, or open it after the server has shut down.

Why both: Claude Code (VS Code) strips file://, vscode://, and command:// URL schemes from chat markdown, so only http:// produces a working clickable link. The file:// path is provided for sharing and offline viewing. Tool annotations (readOnlyHint, idempotentHint, openWorldHint) help clients reason about tool behavior.

Configuration

All optional. Defaults are safe - set these only if you need to override.

Env var

Default

What it does

MCP_DASHBOARDS_RETAIN_DAYS

7

How long to keep chart preview HTML files on disk. 0 disables auto-cleanup.

MCP_DASHBOARDS_DISABLE_PREVIEW

unset

Kill switch - no HTML files written, no preview server started, no preview links. Inline rendering still works in MCP Apps clients.

MCP_HTTP_BIND_HOST

127.0.0.1

HTTP-transport bind host. Stays on localhost by default. Set to 0.0.0.0 only if you trust your network.

MCP_CORS_ALLOWED_ORIGINS

localhost only

Comma-separated origins allowed to call the HTTP endpoint from a browser. Set this to add a non-localhost origin (e.g. https://your-app.com).

MCP_URL_ALLOWLIST

empty

Comma-separated hostnames that bypass the SSRF guard for render_from_url / poll_http. Use only for internal endpoints you fully trust.

MCP_OUTBOUND_RATE_PER_SEC

10

Per-host throttle for outbound HTTP calls.

MCP_OUTBOUND_BURST

20

How many initial requests can fire immediately before the rate kicks in.

POLL_PRESET_<NAME>_URL

-

Server-side preset URL for live polling. See Live Polling.

POLL_PRESET_<NAME>_HEADERS

-

Auth headers (JSON object) for the matching preset URL.

What's on disk

Chart HTML files are written to <system temp>/mcp-dashboards/ and auto-deleted after 7 days. The chart's built-in download button (PNG / PPT / A4) is the recommended way to save anything permanently.

Ask your AI to "list chart files" or "delete chart files older than 1 day" anytime - invokes list_chart_files / delete_chart_files.

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

Built by Rishabh Dogra - connect on LinkedIn.

Privacy

All processing happens locally. No data is collected, transmitted, or stored externally.

External calls only happen when you explicitly ask - render_from_url and poll_http need a URL or preset you provide. Both refuse to fetch private, loopback, or link-local addresses (your 192.168.* network, AWS metadata at 169.254.169.254, etc.) so a prompt-injected AI can't quietly reach internal services. They also throttle per hostname so a runaway loop won't get your IP banned from a real API.

Credentials in env var presets never leave your machine. The browser preview server and the optional HTTP transport both bind to 127.0.0.1 by default and are not reachable from other devices. Chart HTML files live in your system temp folder and auto-delete after 7 days. See Configuration to change any of this.

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.

Third-party software

The bundled UI artifact (dist/mcp-app.html) embeds open-source libraries from the Chart.js, html2canvas-pro, Luxon, TopoJSON, and Dagre projects, distributed under MIT or ISC licenses. Full attribution and license texts are reproduced in THIRD_PARTY_LICENSES.md.

Available Tools

40 tools
delete_chart_filesA
Destructive

Delete chart preview HTML files saved on disk (in the system temp folder). REQUIRES the user's explicit instruction to run - it deletes files from disk and cannot be undone. Provide at least one of: chartIds (specific file IDs to delete), olderThanDays (bulk delete by age), or all=true (delete every chart file). Scope is hard-locked to mcp-dashboards temp folder; cannot touch anything else. Returns lists of successfully deleted files and per-file failures (e.g. files currently locked by an open browser).

Inputs: all, chartIds, olderThanDays.

list_chart_filesA
Read-onlyIdempotent

List all chart preview HTML files saved on disk (in the system temp folder). These are auto-generated each time a chart is rendered and auto-cleaned after 7 days (configurable via MCP_DASHBOARDS_RETAIN_DAYS env var). Returns file metadata (id, name, size, age). Use this to audit disk usage, then call delete_chart_files to remove specific files or all of them.

Inputs: no named parameters.

poll_httpA
Read-only

Fetch JSON from an HTTP endpoint. Used by render_live_chart to poll external APIs. No presets configured. Use "preset" for authenticated APIs (credentials stored server-side in env vars, never exposed). Use "url" only for public APIs that need no authentication. NEVER pass API keys or tokens in the "headers" argument - configure a preset instead.

Inputs: url, body, method, preset, +1 more.

render_bar_chartBar ChartA
Read-onlyIdempotent

Render an interactive bar chart. Supports vertical/horizontal, stacked, multi-series, and click-to-drill-down (options.drilldown). Supports themes for styled visuals.

Inputs: title (required), labels (required), datasets (required), theme, +4 more.

render_boxplot_chartBoxplot / ViolinA
Read-onlyIdempotent

Render a boxplot or violin chart - 'What is the distribution?' Shows median, quartiles, whiskers, and outliers. Pass raw number arrays per category - stats computed automatically. Use style='violin' for density shape.

Inputs: title (required), labels (required), datasets (required), theme, +4 more.

render_bubble_mapBubble MapB
Read-onlyIdempotent

Render a bubble/pin map - sized circles at geographic coordinates. Pass an array of { label, latitude, longitude, value } points. Great for showing city-level data, office locations, event density, etc.

Inputs: data (required), title (required), theme, effects, +6 more.

render_bullet_chartBullet ChartA
Read-onlyIdempotent

Render bullet charts - 'Are we hitting target?' Horizontal bars with qualitative zones and a target marker. Supports 2-8 zones with optional labels and colors. Great for KPI vs target, seniority bands, maturity models.

Inputs: data (required), title (required), theme, effects, +4 more.

render_candlestick_chartCandlestick ChartA
Read-onlyIdempotent

Render an interactive candlestick or OHLC financial chart. Provide date/OHLC data for stock prices, crypto, forex, or any time-series financial data. Supports themes for styled visuals.

Inputs: data (required), title (required), theme, effects, +3 more.

render_catalogMaster CatalogA
Read-onlyIdempotent

Master entry point to discover everything mcp-dashboards can do. Each tile is a live visual preview of one 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 then hit Ask, and the AI will route to the matching sub-catalog tool (render_chart_catalog, render_theme_catalog, render_hero_catalog, render_effects_catalog).

Inputs: theme.

render_chart_catalogChart CatalogA
Read-onlyIdempotent

Show a visual catalog of every available chart type as a dashboard of mini previews. Click any card to learn more about that chart tool. For a master entry point covering all customization dimensions, see render_catalog.

Inputs: theme.

render_dashboardDashboardB
Read-onlyIdempotent

Render a full dashboard with KPI cards, charts, and optional hero metric in a responsive grid. Available themes: boardroom (investors, board decks), corporate (enterprise daily use), sales-floor (quota tracking, leaderboards), golden-treasury (wealth, luxury real estate), clinical (healthcare, compliance - WCAG AAA), startup (SaaS metrics, YC demos), ops-control (DevOps, manufacturing), tokyo-midnight (crypto, trading, gaming), zen-garden (wellness, sustainability), consultant (agency deliverables, presentations), office-red (corporate report-style, Word/PowerPoint aesthetic). Mix-and-match: set palette + typography + effects independently.

Inputs: title (required), charts (required), hero, kpis, +7 more.

render_dumbbell_chartDumbbell ChartB
Read-onlyIdempotent

Render a dumbbell chart - 'How big is the gap?' Before/after dots connected by a bar. Supports scale labels and background zones for absolute positioning context.

Inputs: data (required), title (required), unit, theme, +9 more.

render_effects_catalogEffects CatalogA
Read-onlyIdempotent

Show a visual catalog of all 5 effect presets - none, subtle, shimmer, neon, energetic. Each card previews the effect and lists the underlying treatments it bundles. Click any card to use that effect. For a master entry point covering all customization dimensions, see render_catalog.

Inputs: no named parameters.

render_flowchartFlowchartA
Read-onlyIdempotent

Render an interactive flowchart or diagram. USE THIS whenever the user wants to visualize a flow or structure: a workflow, data pipeline / ETL, system or software architecture, multi-agent or LLM agent design, decision tree, process map, org chart, or state machine. Nodes are rich cards (6 kinds: agent / tool / decision / data / input / output) with a type chip, name, and up to 3 property rows (e.g. model, tokens, latency); pass icon for a custom glyph. Edges support 5 typed kinds (request / response / async / stream / error) with distinct styles. Dagre auto-layout (DAG); draggable, zoomable, pannable, with a node list, minimap, and step-through playback. Status states (queued / running / done / failed / skipped) animate in place: set pollTool + statusPath for live updates, or pass a steps sequence of {nodeId: status} snapshots for manual playback. Do NOT hand-author x/y coordinates to position nodes - omit them and dagre auto-lays out the graph cleanly. Only pass x/y that were round-tripped back to you from a previous render (a user's saved drag layout), and only as a complete set covering every node; a partial set is ignored to prevent overlaps. This is a full-canvas tool, not a dashboard tile - for multi-chart layouts use render_dashboard.

Inputs: edges (required), nodes (required), title (required), steps, +11 more.

render_from_jsonAuto ChartA
Read-onlyIdempotent

Automatically detect the best chart type for arbitrary JSON data. Pass any JSON - arrays, objects, nested structures - and get the most appropriate visualization.

Inputs: data (required), title (required), options.

render_from_urlChart from URLA
Read-only

Fetch JSON data from a URL and automatically visualize it. The server fetches the data, detects the best chart type, and renders it interactively.

Inputs: url (required), title (required), options.

render_funnel_chartFunnel ChartA
Read-onlyIdempotent

Render a funnel chart - 'Where do we lose people?' Width-proportional bars showing conversion stages with optional conversion percentages between stages.

Inputs: data (required), title (required), theme, effects, +3 more.

render_geo_chartGeo MapA
Read-onlyIdempotent

Render a choropleth world map - 'Where is the value concentrated?' Color-coded countries by numeric value. Pass data as { countryCode: value } using ISO 3166-1 alpha-2 codes (US, DE, IN, GB, etc.).

Inputs: data (required), title (required), theme, effects, +6 more.

render_heatmap_chartHeatmapB
Read-onlyIdempotent

Render a heatmap - 'When are patterns strongest?' Color-coded grid of values across rows and columns. Supports color scales: default (blue-purple-orange), red-green, blue, heat.

Inputs: rows (required), title (required), values (required), columns (required), +5 more.

render_hero_catalogHero Variant CatalogA
Read-onlyIdempotent

Show all 11 hero metric variants in a single dashboard - big_number, progress_ring, status, comparison, rank, countdown, threshold, breakdown, nps, orb, gem. Each card is a working preview with sample data. Click any card to learn about that variant.

Inputs: theme.

render_hero_metricHero MetricA
Read-onlyIdempotent

Render a purpose-driven hero metric widget. Pick the variant that answers your question:

  • big_number: 'How much? Which direction?' Default hero metric - clean, professional, works in any context. Large value + trend arrow + optional sparkline. Params: value, unit, change, changePeriod, sparkline[]

  • progress_ring: 'How close to goal?' Animated ring or half-gauge. Params: value, unit, label, progress (0-100), style ('ring'|'gauge'), size, color

  • status: 'Good or bad?' Pulsing dot + subsystem badges. Params: label, statusLevel ('good'|'warn'|'bad'), subsystems[{name,status}], count, peak

  • comparison: 'How do we compare?' Before/after + improvement. Params: before, after, improvement, beforeLabel, afterLabel

  • rank: 'Where do I stand?' Badge + percentile. Params: rank, total, percentile, rankChange

  • countdown: 'How long left?' Time segment boxes. Params: segments[{value,label}] OR deadline (ISO date)

  • threshold: 'Above or below limit?' Gradient bar + marker. Params: value, max, threshold, unit, zones[{label,from,to,color}]

  • breakdown: 'What is the split?' Stacked bar + legend. Params: items[{label,value,color?}]

  • nps: 'How satisfied?' Score + rating scale. Params: value, max (default 100), rating ('good'|'neutral'|'bad')

  • orb: 'What is the headline?' Dramatic glowing sphere. Use golden orb for resumes/portfolios. For tech meetings use only black, white, or crystal-colored orbs as subtle flair. Best with dark themes (tokyo-midnight, ops-control, startup). Avoid for formal contexts (boardroom, clinical, consultant). Params: value, unit, label, color

  • gem: 'Premium gem metric' Faceted/spherical gem - for wealth, fintech, trading, crypto, luxury contexts ONLY. Best with golden-treasury, tokyo-midnight themes. Do NOT use for corporate, clinical, consultant, or boardroom dashboards - use big_number instead. Params: value, unit, label, gemType. gemTypes: crystal='Future' (forecasts, projections) | black_pearl='Rare find' (alt investments, crypto) | golden_pearl='Treasure' (gold, commodities) | white_pearl='Clean total' (savings) diamond='Crown number' (net worth, total revenue) | ruby='What's critical' (urgent, burn rate) | sapphire='Foundation' (stability, uptime) | emerald='Growth' (YoY, appreciation)

Inputs: title (required), max, peak, rank, +33 more.

render_line_chartLine ChartB
Read-onlyIdempotent

Render an interactive line or area chart. Supports smooth curves, gradient fill, and multiple series. Supports themes for styled visuals.

Inputs: title (required), labels (required), datasets (required), theme, +4 more.

render_live_chartLive ChartA
Read-onlyIdempotent

Render a real-time auto-updating line chart that polls a tool at a regular interval. Use when the user wants to MONITOR a live data source. Set pollTool to 'poll_http' with pollArgs containing a preset or URL to poll external APIs (including other MCP servers' data). The chart auto-refreshes - no user action needed.

Inputs: title (required), values (required), pollTool (required), yMax, +10 more.

render_lollipop_chartLollipop ChartA
Read-onlyIdempotent

Render a lollipop chart - 'How do segments compare?' Horizontal lines with dots at the value. Supports optional target markers for benchmarking. Clean alternative to bar charts for ranked data.

Inputs: data (required), title (required), theme, effects, +2 more.

render_pie_chartPie ChartA
Read-onlyIdempotent

Render an interactive pie or donut chart from key-value data. Provide an array of {label, value} pairs. Supports themes for styled visuals.

Inputs: data (required), title (required), theme, effects, +3 more.

render_radar_chartRadar ChartA
Read-onlyIdempotent

Render a radar (spider/web) chart - 'How do items compare across multiple dimensions?' Great for skill profiles, product comparisons, competitive analysis.

Inputs: title (required), labels (required), datasets (required), theme, +4 more.

render_radial_clusterRadial ClusterA
Read-onlyIdempotent

Render a radial cluster - 'Multi-metric health check?' Multiple small ring gauges showing percentage metrics with status colors. Optional alert message.

Inputs: title (required), metrics (required), alert, theme, +3 more.

render_sankey_chartSankey DiagramA
Read-onlyIdempotent

Render a sankey flow diagram - 'Where does it go?' Shows flows between nodes with width proportional to value. Great for budget flows, user journeys, energy transfers, conversion funnels with multiple paths.

Inputs: data (required), title (required), theme, effects, +3 more.

render_scatter_chartScatter ChartB
Read-onlyIdempotent

Render an interactive scatter plot with x/y coordinate data. Supports multiple series and optional connecting lines. Supports themes for styled visuals.

Inputs: title (required), datasets (required), theme, effects, +3 more.

render_slope_chartSlope ChartA
Read-onlyIdempotent

Render a slope chart - 'How did rankings change?' SVG lines connecting two time periods showing relative position changes.

Inputs: data (required), title (required), periodEnd (required), periodStart (required), +4 more.

render_sparkline_chartSparkline CardsA
Read-onlyIdempotent

Standalone sparkline card grid. Prefer using KPI cards with sparkline[] inside render_dashboard instead for a cleaner integrated look.

Inputs: data (required), title (required), theme, effects, +2 more.

render_tableData TableB
Read-onlyIdempotent

Render a sortable, interactive data table. Click column headers to sort. Supports themes for styled visuals.

Inputs: rows (required), title (required), columns (required), theme, +4 more.

render_theme_catalogTheme CatalogA
Read-onlyIdempotent

Show a visual catalog of all 21 available themes. Each card previews the theme's colors, typography, and effects. Click any card to use that theme. For a master entry point covering all customization dimensions, see render_catalog.

Inputs: no named parameters.

render_timeline_chartTimelineA
Read-onlyIdempotent

Render a timeline - 'Where are we in the process?' Progress dots on a track with status colors (done, active, pending, blocked). Great for project milestones. Use horizontal for ≤8 items (better for slides), vertical for longer lists.

Inputs: title (required), milestones (required), theme, effects, +4 more.

render_treemap_chartTreemapA
Read-onlyIdempotent

Render a treemap - 'What takes up the most space?' Nested rectangles sized by value. Supports optional grouping for hierarchical data (e.g. region > country). Great for budget breakdowns, disk usage, portfolio allocation.

Inputs: data (required), title (required), theme, effects, +3 more.

render_variance_chartVariance ChartB
Read-onlyIdempotent

Render a variance chart - 'Over or under budget?' Bars showing actual vs budget with color-coded over/under indicators.

Inputs: data (required), title (required), unit, theme, +3 more.

render_waffle_chartWaffle ChartA
Read-onlyIdempotent

Render a waffle chart - 'What is the composition?' 10x10 grid of colored squares showing proportional composition. Values should sum to 100.

Inputs: data (required), title (required), theme, effects, +2 more.

render_waterfall_chartWaterfall ChartA
Read-onlyIdempotent

Render a waterfall chart - 'What drove the change?' Cascading bars showing how individual items add up or subtract to reach a total. Auto-infers add/sub/total if type omitted.

Inputs: data (required), title (required), unit, theme, +3 more.

render_wordcloud_chartWord CloudA
Read-onlyIdempotent

Render a word cloud - 'What are the dominant themes?' Words sized by frequency or importance. Great for survey responses, keyword analysis, topic frequency.

Inputs: data (required), title (required), theme, effects, +3 more.

save_fileSave FileA
Idempotent

Save a chart export (PNG or CSV) to the user's Downloads folder. App-only - invoked by the chart View's Download buttons, not by the AI.

Inputs: data (required), encoding (required), filename (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 40 tools

    Disambiguation4/5

    Most tools map to a clearly distinct chart type (pie, scatter, funnel, sankey, heatmap, etc.) and descriptions even frame each with a unique question like 'Where do we lose people?', which aids selection. There is some overlap among comparison-oriented charts (bar vs lollipop vs bullet vs waffle) and between render_from_json/render_from_url and the explicit renderers, but boundaries remain workable.

    Naming Consistency4/5

    A strong render_<thing> prefix dominates the set, with file ops consistently using verb_noun (list_chart_files, delete_chart_files, save_file) and poll_http fitting the pattern. Minor deviation: some renders carry a _chart suffix while others (render_table, render_flowchart, render_dashboard, render_radial_cluster, render_bubble_map) do not, but the convention is still predictable.

    Tool Count3/5

    40 tools is heavy for any server and sits in the 'too many' range. The breadth is partly justified since each chart type is a genuinely distinct visualization, but the surface feels large and could likely be consolidated (e.g. catalog tools, sparkline vs dashboard KPI cards).

    Completeness4/5

    Coverage is broad: dozens of chart types, a dashboard compositor, auto-detection from JSON/URL, live polling, discovery catalogs, and temp-file lifecycle management (list/delete). Minor gaps exist, such as export being app-only (save_file not AI-invocable) and no AI-facing way to edit or re-export a rendered chart.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers