MCP Kanban Memory
Manage complex AI agent workflows with a Kanban-based task management system.
MCP Kanban Task Management
An MCP tool set providing kanban-based task management state for AI-driven development. This is similar to other task management MCP tools, with the additional structure, rules and visibility of a kanban-based task management system.
The main idea is to direct the AI agent to document and save its work as tasks in a kanban board, both in the planning session and in execution sessions.
Highlights
- Column capacity / work-in-progress limits
- Embedded DB (SQLite)
- Web UI for observing the progress of the workflow, and for modifying tasks manually
- Predefined prompts for starting and resuming a workflow
Usage
Use the MCP prompts to start a project or to make progress on a project. Alternatively, ask the LLM assistant to record its plan by creating a kanban board. To make progress in a follow-up session, ask the assistant to locate a specific kanban board and resume work on it.
Installation
Clone this repo, then run:
npm ci --prefix shared/db
npm ci --prefix mcp-server
npm run build --prefix shared/db
npm run build --prefix mcp-server
Then add the MCP server configuration to the MCP client (e.g. Claude Desktop):
"mcpServers": {
"kanban-mcp": {
"command": "node",
"args": [
"/path/to/repo/mcp-server/dist/server.js"
],
"env": {
"MCP_KANBAN_DB_FOLDER_PATH": "/path/to/db"
}
}
}
Replace /path/to/repo with the location of the cloned repo.
Replace /path/to/db with a folder that will contain the DB files. This can be any folder with read/write access. It will be created if it doesn't exist.
Installation with Docker
Build the Docker image:
docker build -t mcp/mcp-kanban .
Then add the MCP server configuration to the MCP client (e.g. Claude Desktop):
"mcpServers": {
"kanban-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"/path/to/db:/mcp",
"mcp/mcp-kanban"
]
}
}
Replace /path/to/db with a folder that will contain the DB files. This can be any folder with read/write access. It will be created if it doesn't exist.
Using the web UI
Build the web-ui and web-server:
npm ci --prefix shared/db
npm run build --prefix shared/db
npm ci --prefix web-ui
npm ci --prefix web-server
npm run build --prefix web-ui
npm run build --prefix web-server
Run the web-server:
MCP_KANBAN_DB_FOLDER_PATH=/path/to/db npm run start --prefix web-server
Open the browser at http://localhost:8221
API
Tools
-
create-kanban-board
- Create a new kanban board to plan and keep track of your tasks.
- Input:
name(string): The name of the boardprojectGoal(string): The goal of the project.
-
add-task-to-board
- Add a new task to the landing column (to-do) of a kanban board.
- Input:
boardId(string): The ID of the board to add the task totitle(string): The title of the taskcontent(string): The content of the task in markdown format
-
move-task
- Move a task from one column to another, respecting WIP limits.
- Input:
taskId(string): The ID of the task to movetargetColumnId(string): The ID of the column to move the task toreason(string, optional): The reason for moving the task
-
delete-task
- Delete a task.
- Input:
taskId(string): The ID of the task to delete
-
get-board-info
- Get the full info of a kanban board, including columns and tasks.
- Input:
boardId(string): The ID of the board to get info for
- Return detailed information about the board, including columns and tasks.
-
get-task-info
- Get the full info of a task, including its content.
- Input:
taskId(string): The ID of the task to get info for
- Return detailed information about the task, including its content.
-
list-boards
- List all kanban boards in the database.
- Input: None
- Return a list of all boards in the database with their names, creation times, and goals.
Prompts
-
create-kanban-based-project
- Create a kanban board for a project, ask questions to divide the project into tasks, and add them to the board.
- Input:
description(string): The description of the project
-
make-progress-on-a-project
- Make progress on an existing project by locating its kanban board, selecting the next task, and working on it.
- Input:
description(string): The description of the project
Serveurs connexes
Kone.vc
sponsorMonetize your AI agent with contextual product recommendations
MCP Task Orchestrator
A Kotlin MCP server for comprehensive task management, allowing AI assistants to interact with project data.
WeRead
Access your WeChat Reading (微信读书) bookshelf, notes, highlights, and reviews.
Redmine MCP
Integrates Claude AI with the Redmine project management system to enhance project management tasks.
Heimdall
The all-seeing guardian for macOS: Battery, Clipboard, TTS, and File System control using Claude desktop
Fraud Detection Engine
中英双语 AI 欺诈文本检测引擎,可识别诈骗、钓鱼等风险,返回风险评分、判定和等级。
ffl-mcp
Give AI a "send file" capability via P2P (Local-first)
Scrapbox/CoSense
A server for the Scrapbox/CoSense platform to retrieve, list, search, and create pages.
Wiki.js
Integrates with Wiki.js, enabling AI to read and update documentation.
Reepl MCP
Create, schedule, and publish LinkedIn posts directly from Claude Desktop or ChatGPT through natural conversations
MCP Calendar Assistant
An intelligent assistant for managing calendars and tasks.