Get the FREE Ultimate OpenClaw Setup Guide →

kanbanflow

Model Context Protocol (MCP) server for KanbanFlow - manage boards, tasks, and workflows from Cursor/Claude

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio williamavholmberg-kanbanflow-mcp-server node /path/to/kanbanflow-mcp-server/build/index.js \
  --env KANBAN_API_TOKEN="your_api_token_here"

How to use

KanbanFlow MCP Server exposes a set of MCP endpoints that let you manage KanbanFlow boards, tasks, subtasks, labels, comments, and more directly from Cursor/Claude. The server includes a comprehensive toolkit for common Kanban operations such as retrieving board structures, listing and updating tasks, creating tasks with subtasks, moving tasks between columns, assigning due dates and labels, and adding comments. It also supports advanced workflows like creating tasks with multiple subtasks in one go, updating custom fields, and bulk-handling subtasks. Use the provided commands through the MCP surface to integrate KanbanFlow actions into your Cursor or Claude prompts and automations. The setup wizard auto-detects installations, preserves existing MCP configurations, and generates a clean, path-correct configuration file that you can back up and re-use. The example configuration shows how to run the MCP server via Node.js and how to supply your KanbanFlow API token as an environment variable for authentication.

Typical workflows include querying your board structure, creating tasks in specific columns, adding subtasks, applying labels, and updating task properties like due dates or status. You can mix and match these operations in prompts to automate project management tasks, reduce manual data entry, and keep your KanbanFlow boards in sync with other tools in your workflow.

How to install

Prerequisites:

  • Node.js and npm installed on your machine
  • Git installed for cloning the repository (optional if using npm install)
  • Access to a KanbanFlow API token

Install via npm (recommended for most users):

  1. Install the MCP server globally npm install -g kanbanflow-mcp-server

  2. Run the auto-setup in your project (recommended) cd /path/to/your/project kanbanflow-mcp-server --setup

If you prefer to build from source:

  1. Clone the repository git clone https://github.com/williamavholmberg/kanbanflow-mcp-server cd kanbanflow-mcp-server

  2. Install dependencies and build npm install npm run build

  3. Run the setup in your project (same wizard works here too) kanbanflow-mcp-server --setup

Manual configuration (advanced):

  • The wizard can generate a config entry similar to the following, which you can adapt to your environment:
{
  "mcpServers": {
    "kanban-flow": {
      "command": "node",
      "args": ["/path/to/kanbanflow-mcp-server/build/index.js"],
      "env": {
        "KANBAN_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Notes:

  • The setup wizard preserves existing MCP servers and creates backups before changes.
  • It merges new configuration intelligently with your current setup.
  • Ensure your KanbanFlow API token is provided via the KANBAN_API_TOKEN environment variable.

Additional notes

Tips and common issues:

  • Keep backups of mcp.json or your MCP configuration before running setup, especially in production environments.
  • The setup wizard performs path resolution to avoid binary issues; ensure your project has a stable working directory when running --setup.
  • If you upgrade or change server paths, re-run the wizard to update paths and merge with existing entries safely.
  • Environment variables: besides KANBAN_API_TOKEN, you can add other environment-specific vars as needed by your deployment.
  • This MCP server is designed to work across macOS, Windows, and Linux; if you encounter path or permission issues, run with appropriate user permissions or adjust PATH accordingly.

Related MCP Servers

Sponsor this space

Reach thousands of developers