MCP Dashboards
π π π πͺ π§ - 45+ interactive chart types (bar, line, pie, candlestick, sankey, geo, radar, funn
What is MCP Dashboards?
MCP Dashboards is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to π π π πͺ π§ - 45+ interactive chart types (bar, line, pie, candlestick, sankey, geo, radar, funn
π π π πͺ π§ - 45+ interactive chart types (bar, line, pie, candlestick, sankey, geo, radar, funn
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP protocol support
Use Cases
Maintainer
Works with
Installation
NPM
npx -y mcp-dashboardsManual Installation
npx -y mcp-dashboardsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Dashboards
MCP Dashboards is an interactive charting and dashboard server that gives AI assistants the ability to render over 45 chart types β including bar, line, pie, candlestick, Sankey, treemap, geo choropleth, and word cloud β as interactive HTML outputs rather than static images. It runs entirely locally with no CDN dependencies and supports live data polling from authenticated APIs, multi-chart dashboard grids, and one-click export to PowerPoint, A4 PDF, or PNG. Teams use it to turn conversational data requests into shareable, interactive dashboards without leaving their AI workflow.
Prerequisites
- Node.js 18 or higher
- An MCP-compatible client such as Claude Desktop or Claude Code
- No external API keys required for basic chart rendering (API keys needed only for live-polling private endpoints)
Install via npx (no global install needed)
MCP Dashboards is published to npm as mcp-dashboards and can be run directly with npx. No separate installation step is required β npx downloads and caches the package on first use.
npx -y mcp-dashboards --stdioAdd the server to Claude Desktop config
Open your claude_desktop_config.json and add the dashboard entry. The --stdio flag is required when running as a local MCP server. For VS Code or Claude Code, use the claude mcp add command instead.
{
"mcpServers": {
"dashboard": {
"command": "npx",
"args": ["-y", "mcp-dashboards", "--stdio"]
}
}
}Optionally configure live-polling presets
To poll authenticated APIs, add POLL_PRESET environment variables. The server stores credentials server-side and never exposes them in chart output. Replace NAME with a short label you will reference in prompts.
{
"mcpServers": {
"dashboard": {
"command": "npx",
"args": ["-y", "mcp-dashboards", "--stdio"],
"env": {
"POLL_PRESET_METRICS_URL": "https://api.example.com/metrics",
"POLL_PRESET_METRICS_HEADERS": "{\"Authorization\": \"Bearer YOUR_TOKEN\"}"
}
}
}
}Restart your MCP client and verify tools
Fully restart Claude Desktop. The 31 dashboard tools will appear, covering individual chart types, multi-chart dashboards, auto-detect rendering, and live-poll charts. Ask Claude to list available chart tools to confirm.
Request a chart in natural language
Simply describe the visualization you want in a prompt. The server renders interactive HTML with hover tooltips, zoom, and drill-down. Use the export option to save as PowerPoint, PDF, or PNG when needed.
MCP Dashboards Examples
Client configuration
Standard claude_desktop_config.json entry for MCP Dashboards using npx with the required --stdio flag.
{
"mcpServers": {
"dashboard": {
"command": "npx",
"args": ["-y", "mcp-dashboards", "--stdio"]
}
}
}Prompts to try
Sample prompts covering common chart types, themes, live polling, and export workflows.
- "Compare Q1 vs Q2 revenue by region as a bar chart using the boardroom theme"
- "Show our product portfolio allocation as a donut chart"
- "Create a Sankey diagram showing user flow from landing page to checkout"
- "Plot a candlestick chart for AAPL with the last 30 trading days of data"
- "Build a dashboard with a line chart of monthly signups and a pie chart of traffic sources side by side"
- "Show a geo choropleth map of sales by US state"Troubleshooting MCP Dashboards
Charts render as links rather than inline visuals in Claude Desktop
Claude Desktop may not support inline HTML rendering in all views. Click the preview link provided in the tool output to open the interactive chart in your browser. Set MCP_DASHBOARDS_DISABLE_PREVIEW=1 in env if you want to suppress these links.
Live-polling chart does not refresh from my API
Check that POLL_PRESET_<NAME>_URL and POLL_PRESET_<NAME>_HEADERS are correctly set in the env block of your MCP config. The NAME portion must match what you reference in the prompt. Restart Claude Desktop after changing env vars.
npx takes a long time or fails on first run
npx downloads mcp-dashboards from the npm registry on first use. Ensure internet connectivity and Node.js 18+. Run `npx -y mcp-dashboards --version` in a terminal to pre-cache the package and confirm it downloads correctly.
Frequently Asked Questions about MCP Dashboards
What is MCP Dashboards?
MCP Dashboards is a Model Context Protocol (MCP) server that π π π πͺ π§ - 45+ interactive chart types (bar, line, pie, candlestick, sankey, geo, radar, funn It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Dashboards?
Install via npm with the command: npx -y mcp-dashboards. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with MCP Dashboards?
MCP Dashboards works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Dashboards free to use?
Yes, MCP Dashboards is open source and available under the Functional Source License, Version 1.1, MIT Future License license. You can use it freely in both personal and commercial projects.
MCP Dashboards Alternatives β Similar Analytics Servers
Looking for alternatives to MCP Dashboards? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
β 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
β 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
β 4.4kπ‘ Your own AI-powered news radar. Generates daily briefings in English & Chinese. | η¨ AI ζε»Ίδ½ δΈε±ηζ°ι»ι·θΎΎ
MCP Server Chart
β 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
β 997Official CLI for muapi.ai β generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
β 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Dashboards in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Dashboards?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.