drio
Open app

TaskBoardAI

Source

Kanban board designed for ai agents to keep track of multi-step tasks. Includes HIL Web UI and MCP server.

Catalog onlyCatalog onlySTDIO

Overview

TaskBoardAI is a Kanban board designed specifically for AI agents to manage and keep track of multi-step tasks efficiently. It features a HIL Web UI and an MCP server for seamless operation.

To use TaskBoardAI, set up the HIL Web UI and connect it to the MCP server. You can then create, manage, and monitor tasks assigned to AI agents through the intuitive interface.

  • Designed for AI agents to manage multi-step tasks - HIL Web UI for user-friendly interaction - MCP server for backend task management
  1. Managing complex workflows for AI projects
  2. Tracking progress of AI agents on multi-step tasks
  3. Visualizing task dependencies and statuses in a Kanban format

Add to your AI client

Use these steps to connect TaskBoardAI in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "taskboardai-tuckertucker": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-taskboardai-tuckertucker"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "taskboardai-tuckertucker": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-taskboardai-tuckertucker"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "taskboardai-tuckertucker": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-taskboardai-tuckertucker"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "taskboardai-tuckertucker": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-taskboardai-tuckertucker"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "taskboardai-tuckertucker": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-taskboardai-tuckertucker"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "taskboardai-tuckertucker": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-taskboardai-tuckertucker"
      ]
    }
  }
}

FAQ

Can TaskBoardAI be used for non-AI projects?

While TaskBoardAI is optimized for AI agents, it can also be adapted for general project management tasks.

Is TaskBoardAI open source?

Yes! TaskBoardAI is available under the Apache-2.0 license on GitHub.

How can I contribute to TaskBoardAI?

Contributions are welcome! You can submit issues or pull requests on the GitHub repository.

Developer tools