Model Context Protocol (MCP) Server for Kanboard Integration

A powerful Go-based MCP server that enables seamless integration between AI assistants (like Claude Desktop, Cursor) and Kanboard project management system. Manage your Kanboard projects, tasks, users, and workflows directly through natural language commands.

⚠️ Warning: To avoid issues like these:

We recommend using mcpproxy as a proxy solution.

• ✨ Features
• 🚀 Quick Start
• ⚙️ Configuration
• 🛠️ Available Tools
• 📖 Usage Examples
• 🔧 Development
• 📄 License

• 🔗 Seamless Kanboard Integration - Direct API communication with Kanboard
• 🤖 Natural Language Processing - Use plain English to manage your projects
• 📊 Complete Project Management - Handle projects, tasks, users, columns, and more
• 🔐 Secure Authentication - Support for both API key and username/password auth
• ⚡ High Performance - Built with Go for optimal performance
• 🎯 MCP Standard - Compatible with all MCP clients

• Go 1.21 or higher
• Kanboard instance with API access
• MCP-compatible client (Cursor, Claude Desktop, etc.)

1. Clone the repository:

   git clone https://github.com/bivex/kanboard-mcp.git
   cd kanboard-mcp

2. Build the executable:

   On Windows:

   build-release.bat

   On Linux/macOS:

   ./build-release.sh

   Manual build:

   go build -ldflags="-s -w" -o kanboard-mcp .

Set up your Kanboard credentials using environment variables:

export KANBOARD_API_ENDPOINT="https://your-kanboard-url/jsonrpc.php"
export KANBOARD_API_KEY="your-kanboard-api-key"
export KANBOARD_USERNAME="your-kanboard-username"
export KANBOARD_PASSWORD="your-kanboard-password"

Create the MCP configuration file for your client:

Location:

• Windows: C:\Users\YOUR_USERNAME\AppData\Roaming\Cursor\.cursor\mcp_config.json
• Linux/macOS: ~/.cursor/mcp_config.json

Configuration:

{
  "mcpServers": {
    "kanboard-mcp-server": {
      "command": "/path/to/your/kanboard-mcp",
      "args": [],
      "env": {
        "KANBOARD_API_ENDPOINT": "https://your-kanboard-url/jsonrpc.php",
        "KANBOARD_API_KEY": "your-kanboard-api-key",
        "KANBOARD_USERNAME": "your-kanboard-username",
        "KANBOARD_PASSWORD": "your-kanboard-password"
      }
    }
  }
}

After saving the configuration, restart your MCP client (Cursor, Claude Desktop, etc.) for changes to take effect.

# Create a new project
"Create a new project called 'Mobile App Development'"

# Add tasks to the project
"Create task 'Design UI mockups' in project 'Mobile App Development'"
"Create task 'Set up development environment' in project 'Mobile App Development'"

# Get all tasks
"Get tasks for 'Mobile App Development' project"

# Move tasks between columns
"Move task 1 to 'In Progress' column"
"Move task 2 to 'Done' column"

# Create a new team member
"Create user 'alice.smith' with password 'secure123' and email 'alice@company.com'"

# Assign user to project
"Assign user 'alice.smith' to project 'Mobile App Development' as project-member"

# Assign tasks to team members
"Assign task 1 to user 'alice.smith'"

# Create categories for better organization
"Create category 'Critical Bugs'"
"Create category 'Feature Requests'"

# Add comments to tasks
"Add comment 'This needs urgent attention' to task 5"

# Set deadlines
"Set due date for task 3 to 2024-01-20"

# Clone the repository
git clone https://github.com/bivex/kanboard-mcp.git
cd kanboard-mcp

# Install dependencies
go mod download

# Build the application
go build -o kanboard-mcp .

# Run tests
go test ./...

kanboard-mcp/
├── main.go              # Main application entry point
├── go.mod               # Go module dependencies
├── go.sum               # Dependency checksums
├── build-release.bat    # Windows build script
├── build-release.sh     # Unix build script
├── README.md            # This file
└── LICENSE.md           # License information

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE.md file for details.