A task management system with Model Context Protocol (MCP) implementation for seamless integration with agentic AI tools. Enables AI agents to create, manage, and track tasks in plans using Valkey as the persistence layer.

Installation

Docker (SSE)

docker run -d --name valkey-mcp \
  -p 8080:8080 \
  -p 6379:6379 \
  -v valkey-data:/data \
  -e ENABLE_SSE=true \
  ghcr.io/jbrinkman/valkey-ai-tasks:latest

Docker (Streamable HTTP)

docker run -d --name valkey-mcp \
  -p 8080:8080 \
  -p 6379:6379 \
  -v valkey-data:/data \
  -e ENABLE_STREAMABLE_HTTP=true \
  ghcr.io/jbrinkman/valkey-ai-tasks:latest

Docker (STDIO)

docker run -i --rm --name valkey-mcp \
  -v valkey-data:/data \
  -e ENABLE_STDIO=true \
  ghcr.io/jbrinkman/valkey-ai-tasks:latest

Docker Pull

docker pull ghcr.io/jbrinkman/valkey-ai-tasks:latest

Create Volume

docker volume create valkey-data

Configuration

SSE Transport

{
  "mcpServers": {
    "valkey-tasks": {
      "serverUrl": "http://localhost:8080/sse"
    }
  }
}

Streamable HTTP Transport

{
  "mcpServers": {
    "valkey-tasks": {
      "serverUrl": "http://localhost:8080/mcp"
    }
  }
}

STDIO Transport

{
  "mcpServers": {
    "valkey-tasks": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v", "valkey-data:/data"
        "-e", "ENABLE_STDIO=true",
        "ghcr.io/jbrinkman/valkey-ai-tasks:latest"
      ]
    }
  }
}

Docker SSE Transport

{
  "mcpServers": {
    "valkey-tasks": {
      "serverUrl": "http://valkey-mcp-server:8080/sse"
    }
  }
}

Available Tools

Tool	Description
create_plan	Create a new plan
get_plan	Get a plan by ID
list_plans	List all plans
list_plans_by_application	List all plans for a specific application
update_plan	Update an existing plan
delete_plan	Delete a plan by ID
update_plan_notes	Update plan notes
get_plan_notes	Get plan notes
create_task	Create a new task in a plan
get_task	Get a task by ID
list_tasks_by_plan	List all tasks in a plan
list_tasks_by_status	List all tasks with a specific status
update_task	Update an existing task
delete_task	Delete a task by ID
reorder_task	Change the order of a task in a plan

Features

• Plan management (create, read, update, delete)
• Task management (create, read, update, delete)
• Task ordering and prioritization
• Task status tracking
• Markdown-formatted notes support for plans and tasks
• MCP server for AI agent integration
• STDIO, SSE, and Streamable HTTP transport protocol support
• Docker container for easy deployment
• MCP resources for efficient data access
• Bulk task creation in a single operation

Environment Variables

Optional

• ENABLE_SSE — Enable Server-Sent Events transport
• ENABLE_STREAMABLE_HTTP — Enable Streamable HTTP transport
• ENABLE_STDIO — Enable STDIO transport for direct process communication

Usage Examples

I need to organize work for my new application called "inventory-manager". Create a plan for this application with plan notes about creating a comprehensive inventory management system, and add tasks for setting up database schema, implementing REST API endpoints, creating user authentication, designing frontend dashboard, and implementing inventory tracking features.

Notes

The system provides MCP resources for efficient data access with URI patterns like 'ai-tasks://plans/{id}/full' for viewing full plan details. The notes functionality supports full Markdown: headings, lists, tables, code blocks, links, and images. The server automatically selects the transport based on URL path and content type.