chart-mcp
Renders interactive Chart.js charts inside MCP hosts like Claude Desktop, enabling users to switch chart types and regenerate random data without leaving the UI.
README
chart-mcp
An MCP App server that renders an interactive Chart.js chart inside an MCP host (e.g. Claude Desktop). Users can switch between chart types and regenerate random data without leaving the host UI.
Features
- Eight chart types: line, bar, pie, doughnut, radar, polar area, bubble, scatter
- Chart type selector dropdown
- "Regenerate Data" button that fetches fresh random data from the server
- Host theme integration via CSS custom properties
How it works
The server exposes two MCP tools and one resource:
| Name | Type | Description |
|---|---|---|
render-chart |
UI tool | Opens the chart UI in the host. Accepts an optional chartType argument. |
generate-data |
Tool | Returns Chart.js-compatible JSON for the given chart type. Called from the UI. |
ui://chart/mcp-app.html |
Resource | The bundled React + Chart.js single-file HTML served to the host. |
When the host invokes render-chart it reads the _meta.ui.resourceUri field and loads the bundled HTML as an interactive panel. The React UI then calls generate-data via app.callServerTool() whenever data is needed.
Requirements
- Node.js 18+
- npm
Getting started
npm install
npm run build
npm run serve # HTTP transport on port 3001
# or
npm run serve:stdio # stdio transport
During development, Vite watches source files and the server restarts on changes:
npm run dev
Connecting to an MCP host
HTTP transport
Point your MCP host at:
http://localhost:3001/mcp
stdio transport
Use the serve:stdio script as the command in your host configuration:
{
"mcpServers": {
"chart-mcp": {
"command": "npm",
"args": ["run", "serve:stdio"],
"cwd": "/path/to/chart-mcp"
}
}
}
Test host
The @modelcontextprotocol/ext-apps repo ships a browser-based test host:
cd /path/to/mcp-ext-apps/examples/basic-host
npm install && npm run start
# open http://localhost:8080
Enter http://localhost:3001/mcp as the server URL, then invoke render-chart to open the chart UI.
Usage
Once connected, ask the host to call the render-chart tool:
render-chart # defaults to bar chart
render-chart chartType="pie" # open with pie chart selected
Inside the UI:
- Use the Chart Type dropdown to switch chart types — new data is fetched automatically.
- Click Regenerate Data to get fresh random data for the current chart type.
Project structure
chart-mcp/
├── mcp-app.html # Vite HTML entry point
├── main.ts # HTTP + stdio transport entry point
├── server.ts # MCP server: tools, resource, data generation
├── vite.config.ts # Vite + singlefile config
├── tsconfig.json
├── package.json
└── src/
├── mcp-app.tsx # React chart UI
└── global.css # Host CSS variable fallbacks
Scripts
| Script | Description |
|---|---|
npm run build |
Type-check and bundle the UI to dist/mcp-app.html |
npm run dev |
Vite watch + MCP server with live reload |
npm run serve |
Start MCP server (HTTP, port 3001) |
npm run serve:stdio |
Start MCP server (stdio) |
License
Apache 2.0 — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.