The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
CanvasMCPClient
Canvas MCP Client is an open-source, self-hostable dashboard application built around an infinite, zoomable, and pannable canvas. It provides a unified interface for…
Install
git clone https://github.com/n00bvn/CanvasMCPClientInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Canvas MCP Client
A customizable infinite canvas dashboard with integrated Model Context Protocol (MCP) server support
Features • Quick Start • Documentation • Contributing • License
🎯 What is Canvas MCP Client?
Canvas MCP Client is an open-source, self-hostable dashboard application built around an infinite, zoomable, and pannable canvas. It provides a unified interface for interacting with multiple MCP (Model Context Protocol) servers through a flexible, widget-based system.
Why Canvas MCP Client?
- 🎨 Infinite Canvas: Organize your workspace spatially with unlimited zoom and pan capabilities
- 🧩 Modular Widgets: Use 12+ pre-built widgets or create your own custom components
- 🛠️ No-code Widget Builder: Use the widget builder to create your own widgets without coding
- 🤖 MCP Integration: Seamlessly connect to multiple MCP servers using the FastMCP library
- 🔌 AI-Powered: Configure multiple AI providers (OpenAI, Anthropic, Ollama, Google) for enhanced functionality
- 🎭 Template System: Save and share widget and dashboard configurations
- 🐳 Easy Deployment: One-command Docker setup or manual installation
- 🔒 Privacy-First: All data stays on your infrastructure, no external dependencies
Perfect for AI power users, developers, content creators, and anyone who wants a customizable workspace for managing AI tools and services.
🎥 Quick Demo
Click to watch the Canvas MCP Client demo video
✨ Features
Core Functionality
🎨 Infinite Canvas Interface
- Smooth zooming and panning
- Grid snap and alignment tools
- Persistent viewport state
- Responsive and optimized rendering
🧩 Rich Widget System (12+ widgets)
- 📝 Sticky Notes - Quick notes and reminders
- ✅ To-Do Lists - Task management with checkboxes
- 💬 AI Chat - Integrated LLM conversations
- 🖼️ Image Display - Visual content display
- 🃏 Flash Cards - Learning and memorization
- 🎬 Video Player - Media playback
- 📊 Kanban Board - Project management
- 📈 Spreadsheet - Data tables and organization
- 📄 Markdown Editor - Formatted documentation
- 🌐 Webpage Preview - Embedded web content
- 🌍 World Clock - Multiple timezone display
- ☁️ Weather Widget - Live weather information
🔌 MCP Server Management
- Configure multiple MCP server connections
- Support for stdio, HTTP, and SSE transport protocols
- Real-time connection status monitoring
- Import/export server configurations
🤖 AI LLM Configuration
- Multiple AI provider support (OpenAI, Anthropic, Ollama, Google)
- Configurable model parameters
- Secure credential storage
- Custom API endpoints
📦 Template System
- Save widgets as reusable templates
- Export/import dashboard configurations
- Share templates with the community
- Template library with preview
🎨 Customization
- Light and dark themes
- Widget color and shape customization
- Flexible layout options
- Drag-and-drop interface
💾 Data Persistence
- Automatic saving
- Local SQLite storage (PostgreSQL ready)
- Session recovery
- Backup and restore capabilities
🚀 Quick Start
Prerequisites
- Docker & Docker Compose (Recommended) OR
- Node.js 18+ and Python 3.10+ (Manual setup)
Option 1: Docker (Recommended)
The fastest way to get started:
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)