Viban
Viban is a lightweight TypeScript kanban tool that integrates the MCP server protocol, supports AI assistants to directly manage development tasks through protocol tools, and provides a visual interface and file storage.
2.5 points
4.2K

What is Viban?

Viban is an intelligent kanban tool designed for developers, which combines traditional kanban task management with AI assistants. Through the Model Context Protocol (MCP), you can directly manage your development tasks in AI programming assistants such as Claude, Cursor, and Antigravity. AI can view tasks, create new tasks, move task statuses, and even automatically complete workflows.

How to use Viban?

Using Viban is very simple: 1) Install and run the Viban server; 2) Configure the MCP connection in your AI assistant (such as Claude Desktop); 3) Manage tasks through the web interface or directly through the AI assistant. AI can interact with your kanban like a team member to help you track project progress.

Use cases

Viban is particularly suitable for: individual developers managing multiple project tasks, small - team collaborative development, AI - assisted programming workflows, and any development project that requires visual task tracking. It makes AI an intelligent assistant for your project management.

Main features

Four - column kanban workflow
The standard four - column workflow of Backlog (To - do pool) → Todo (In progress) → Review (Under review) → Done (Completed) clearly shows the task status.
AI assistant integration
Seamlessly integrate with AI programming assistants such as Claude, Cursor, and Antigravity through the MCP protocol. AI can directly manage your tasks.
Visual web interface
A simple and beautiful web interface that supports switching between light/dark themes and can be accessed via http://localhost:3000.
9 MCP tools
Provides a complete set of task management APIs, including 9 tools such as getting tasks, creating tasks, updating tasks, moving tasks, and deleting tasks.
File storage
No database is required. All tasks and configurations are stored in JSON and YAML files, which is simple, lightweight, and easy to back up.
Multi - platform support
Supports use in various AI development environments such as Claude Desktop, Cursor, and Antigravity.
Advantages
🤖 AI integration: Let AI be your project management assistant and automate the task management process.
🚀 Lightweight and fast: No database is required. The file storage method makes deployment and operation very simple.
🎨 User - friendly interface: A simple web interface that supports theme switching and provides a good user experience.
🔌 Strong compatibility: Supports multiple AI development environments and can flexibly adapt to different workflows.
📁 Easy to back up: All data is stored in ordinary files, which can be easily backed up and version - controlled.
Limitations
📶 No real - time collaboration: Currently does not support real - time collaborative editing by multiple users.
💾 Storage limitations: The file storage method may not be suitable for ultra - large - scale projects.
🌐 Network requirements: MCP integration requires the AI assistant to support the MCP protocol.
🔧 Configuration steps: Initial configuration requires some technical operations.

How to use

Install Viban
Clone the repository, install dependencies, and then build the project.
Run the Viban server
Run Viban in interactive mode, and it will prompt you to select the project path.
Configure the AI assistant
Add the MCP server configuration in your AI assistant (such as Claude Desktop).
Start using
Access the web interface (http://localhost:3000) or directly manage tasks in the AI assistant.

Usage examples

AI - assisted task management
When you are writing code, the AI assistant can help you manage task statuses, allowing you to focus on coding.
Batch task creation
During the project planning phase, AI can help you quickly create multiple tasks.
Progress tracking
Keep track of project progress at any time. AI can generate a status report for you.

Frequently Asked Questions

Does Viban require an Internet connection?
Where is the data stored? Is it secure?
Does it support team collaboration?
Can I customize the kanban columns?
How do I back up my task data?

Related resources

Model Context Protocol (MCP) official documentation
Understand the technical details and specifications of the MCP protocol.
GitHub repository
The source code and latest version of Viban.
Claude Desktop MCP configuration guide
How to configure the MCP server in Claude Desktop.
Introduction to the kanban method
Understand the basic principles and best practices of the kanban method.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "viban": {
      "command": "node",
      "args": ["/absolute/path/to/viban/dist/index.js", "--mcp"],
      "env": {
        "VIBAN_PROJECT_PATH": "/path/to/your/project"
      }
    }
  }
}

{
  "mcpServers": {
    "viban": {
      "command": "node",
      "args": [
        "c:/Users/Seb/Documents/viban/dist/index.js",
        "--mcp"
      ],
      "env": {
        "VIBAN_PROJECT_PATH": "C:/Users/Seb/Documents/viban_test"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.0K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
4.3K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.5K
4 points
P
Paperbanana
Python
6.8K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.6K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
6.7K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
6.6K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.0K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
74.3K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.6K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.9K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.4K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.8K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.2K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
49.9K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase