mcp -chart-minio
mcp-server-chart私有化部署方案
claude mcp add --transport stdio zaizaizhao-mcp-server-chart-minio node dist/main.js \ --env PORT="3000" \ --env NODE_ENV="production" \ --env MINIO_PORT="9000" \ --env MINIO_USE_SSL="false" \ --env MINIO_ENDPOINT="<minio-service-endpoint>" \ --env PUBLIC_API_URL="http://your-server-ip:3000" \ --env MINIO_ACCESS_KEY="<minio-access-key>" \ --env MINIO_SECRET_KEY="<minio-secret-key>" \ --env MINIO_BUCKET_NAME="charts" \ --env MINIO_AUTO_CREATE_BUCKET="true"
How to use
This MCP server provides a server-side rendering service for generating a variety of charts using MinIO as the object storage backend. It supports 22+ chart types including line, area, column, bar, pie, radar, sankey, treemap, and more, with server-side rendering for fast image generation. The service exposes RESTful endpoints and a documented API, and can store generated chart assets in MinIO and return accessible URLs. To run, you can either use Docker Compose for a complete deployment or run the Node.js application locally for development. Typical usage involves starting the server, then sending JSON payloads to generate charts (e.g., line, pie) via the API endpoints described in the API docs. The setup also includes a MinIO instance for storage, with a web console at / (MinIO default port 9001).
How to install
Prerequisites:
- Node.js v18+ (and npm or yarn)
- Docker and Docker Compose (optional for Docker deployment)
- Git
Install and run locally (development):
- Clone the repository: git clone <repository-url> cd mcp-server-chart-minio
- Install dependencies: npm install
- Start MinIO service (optional if you already have MinIO):
npm run docker:up:minio
or via Docker Compose
docker compose -f docker-compose.minio.yml up -d - Create or edit your local environment file (.env) with MinIO and API settings as needed.
- Run the development server: npm run start:dev
Run in Docker (production-like):
- Ensure you have a docker-compose.minio.yml and .env or .env.production configured.
- Start all services: docker compose --env-file .env.docker up -d
- Access API at http://localhost:3000 (or as configured in PUBLIC_API_URL). API docs at http://localhost:3000/api/docs.
Additional notes
Notes and tips:
- The project relies on MinIO for object storage; configure MINIO_ROOT_USER/MINIO_ROOT_PASSWORD and MINIO_BUCKET_NAME for your environment.
- Multiple .env files are used for different environments (.env for local, .env.docker for Docker, .env.production for production). Ensure the correct file is loaded or explicitly set environment variables.
- If you modify ports, adjust PUBLIC_API_URL and any external endpoint values accordingly.
- For server-side rendering, ensure the system has the required canvas and rendering dependencies installed (as described for local development).
- The API endpoints and request payloads are documented in the API docs URL. Use the provided examples as references for chart-generating requests.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
mcp -chart
🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.
mcp-graphql
Model Context Protocol server for GraphQL
Matryoshka
MCP server for token-efficient large document analysis via the use of REPL state
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
kanban
MCP Kanban is a specialized middleware designed to facilitate interaction between Large Language Models (LLMs) and Planka, a Kanban board application. It serves as an intermediary layer that provides LLMs with a simplified and enhanced API to interact with Planka's task management system.