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

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

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

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)

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.

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.

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.

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.

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.

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).

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

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.

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.

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

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.

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.

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

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.

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

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

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

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.

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.

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).

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.

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.

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.

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

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

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

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

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

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

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.

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.

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.

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.

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.).

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.

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.