
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
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.