KnBn MCP Server
A Model Context Protocol server that provides AI assistants with structured access to kanban board functionality for managing tasks, columns, labels, and sprints.
README
KnBn MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with structured access to kanban board functionality. Built on top of the KnBn CLI tool, this server exposes kanban operations through MCP tools and resources.
Overview
KnBn MCP Server enables AI assistants to interact with kanban boards programmatically using the standardized MCP protocol. It provides three main interaction methods:
- MCP Tools: Interactive operations for creating, updating, and managing boards, tasks, columns, labels, and sprints
- MCP Resources: Read-only access to board data with structured URI patterns
- CLI Integration: Built on the proven KnBn CLI for reliable board operations
Features
- Board Management: Create, list, and migrate kanban boards
- Task Operations: Full CRUD operations including batch updates
- Column Management: Create, update, remove, and list board columns
- Label System: Add, update, remove, and list task labels with colors
- Sprint Management: Create and manage development sprints
- Resource Access: Read-only data access via MCP resources
- Migration Support: Upgrade board files to latest format versions
Installation
As MCP Server
- Install the package:
npm install knbn-mcp
- Configure in your MCP client (e.g., Claude Desktop):
{
"mcpServers": {
"knbn": {
"command": "npx",
"args": ["knbn-mcp"]
}
}
}
For Development
- Clone the repository:
git clone https://github.com/mattbalmer/knbn-mcp.git
cd knbn-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
- Run tests:
npm test
Usage
MCP Tools
The server provides organized tool categories:
Board Tools
list_boards- List all .knbn board filesget_board- Get complete board contentscreate_board- Create new board with name and descriptionmigrate- Migrate board files to latest version
Task Tools
create_task- Create task with title, description, priority, story pointsget_task- Get task details by IDlist_tasks- List/filter tasks by column, label, priority, sprintupdate_task- Update task propertiesupdate_tasks_batch- Update multiple tasks efficiently
Column Tools
create_column- Add new column at specified positionlist_columns- List all columns with optional task countsupdate_column- Rename existing columnremove_column- Delete column
Label Tools
add_label- Create label with name and colorlist_labels- List all available labelsupdate_label- Modify label name or colorremove_label- Delete label from board
Sprint Tools
add_sprint- Create sprint with dates, capacity, descriptionlist_sprints- List sprints filtered by statusupdate_sprint- Modify sprint propertiesremove_sprint- Delete sprint
MCP Resources
Access board data through structured URIs:
knbn://boards- List of all board filesknbn://board/{filename}- Complete board dataknbn://board/{filename}/summary- Board summary with metricsknbn://board/{filename}/tasks- All tasks from a board
Example Usage
// Create a new board
await mcpClient.callTool("create_board", {
name: "Project Alpha",
description: "Development board for Project Alpha",
filename: "alpha.knbn"
});
// Create a task
await mcpClient.callTool("create_task", {
title: "Implement authentication",
description: "Add login and registration functionality",
column: "To Do",
priority: 1,
storyPoints: 5,
labels: ["backend", "security"],
filename: "alpha.knbn"
});
// Move task to different column
await mcpClient.callTool("update_task", {
id: 1,
column: "In Progress",
filename: "alpha.knbn"
});
// Get board summary
const summary = await mcpClient.readResource("knbn://board/alpha.knbn/summary");
Development
Scripts
npm run build- Compile TypeScript to JavaScriptnpm test- Run Jest testsnpm run test:watch- Run tests in watch modenpm run test:coverage- Generate coverage report
Architecture
src/
├── server.ts # Main MCP server entry point
├── patch.ts # MCP SDK extensions
├── tools/ # MCP tools organized by domain
│ ├── board/ # Board management tools
│ ├── tasks/ # Task management tools
│ ├── columns/ # Column management tools
│ ├── labels/ # Label management tools
│ └── sprints/ # Sprint management tools
└── resources/ # MCP resources for data access
└── board-resource.ts
Testing
Tests are located in tests/ with fixtures in tests/fixtures/. Run the test suite:
npm test
Generate coverage report:
npm run test:coverage
Board File Format
Board data is stored in .knbn files using a structured format. The MCP server handles all file operations automatically, but you can also interact with these files directly using the KnBn CLI.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Run the test suite
- Submit a pull request
License
MIT License - see LICENSE for details.
Related Projects
- KnBn CLI - Command-line kanban tool
- KnBn Web - Web interface for KnBn boards
- Model Context Protocol - Protocol specification
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。