TaskFlow MCP 🔄✅
A task management Model Context Protocol (MCP) server for planning and executing tasks with AI assistants.
Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
A task management Model Context Protocol (MCP) server for planning and executing tasks with AI assistants.
A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow with user approval steps.
TaskFlow MCP is a specialized server that helps AI assistants break down user requests into manageable tasks and track their completion. It enforces a structured workflow with user approval steps to ensure tasks are properly tracked and users maintain control over the process.
npm install -g @pinkpixel/taskflow-mcp
npm install @pinkpixel/taskflow-mcp
If installed globally:
taskflow-mcp
If installed locally:
npx taskflow-mcp
By default, TaskFlow MCP saves tasks to tasks.yaml in the current working directory. You can customize this by setting the TASK_MANAGER_FILE_PATH environment variable:
Absolute paths (recommended for production):
TASK_MANAGER_FILE_PATH=/home/user/projects/my-tasks.yaml taskflow-mcp
# Windows
TASK_MANAGER_FILE_PATH=C:\Users\username\Documents\tasks.yaml taskflow-mcp
Relative paths (great for project-based workflows):
# Resolves to ./project-tasks.yaml in the current directory
TASK_MANAGER_FILE_PATH=project-tasks.yaml taskflow-mcp
# Resolves to ./tasks/current.yaml relative to working directory
TASK_MANAGER_FILE_PATH=tasks/current.yaml taskflow-mcp
Advanced: Custom base directory
# Use a different base directory for relative path resolution
TASK_MANAGER_BASE_DIR=/home/user/workspace TASK_MANAGER_FILE_PATH=tasks.yaml taskflow-mcp
TaskFlow MCP automatically handles path resolution across Windows and Linux:
path.resolve() and path.normalize() for consistent behavior/) and backslashes (\) on WindowsTaskFlow MCP supports both JSON and YAML formats for data persistence. To use YAML format, simply configure your file path with a .yaml or .yml extension:
TASK_MANAGER_FILE_PATH=/path/to/tasks.yaml taskflow-mcp
YAML format is particularly useful for:
The format is automatically detected based on the file extension, and the system maintains full backward compatibility with existing JSON files.
TaskFlow MCP v1.4.1 includes a comprehensive archive system to keep your active task lists clean while preserving completed work history:
# Configure archive file path (optional - defaults to [taskfile-name]-archive.[ext])
ARCHIVE_FILE_PATH=/path/to/tasks-archive.yaml taskflow-mcp
# Set archive mode (optional - defaults to 'manual')
ARCHIVE_MODE=manual taskflow-mcp # or 'auto-on-complete'
Archive features include:
archive_completed_requests tool to archive when readyARCHIVE_MODE=auto-on-complete for automatic archivinglist_archived_requestsrestore_archived_requestTo use TaskFlow MCP with AI assistants, you need to configure your MCP client to use the server. Create an mcp_config.json file with the following content:
Basic Configuration:
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": ["-y", "@pinkpixel/taskflow-mcp"],
"env": {
"TASK_MANAGER_FILE_PATH": "/path/to/tasks.yaml"
}
}
}
}
Advanced Configuration (with all v1.4.1 options):
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": ["-y", "@pinkpixel/taskflow-mcp"],
"env": {
"TASK_MANAGER_FILE_PATH": "./project-tasks.yaml",
"TASK_MANAGER_BASE_DIR": "/path/to/project/root",
"ARCHIVE_FILE_PATH": "./tasks-archive.yaml",
"ARCHIVE_MODE": "manual"
}
}
}
}
Configuration Options:
TASK_MANAGER_FILE_PATH: Path to tasks file (supports .json/.yaml, absolute/relative paths)TASK_MANAGER_BASE_DIR: Custom base directory for relative path resolutionARCHIVE_FILE_PATH: Path to archive file (optional, auto-generated if not specified)ARCHIVE_MODE: Archive mode - "manual" (default) or "auto-on-complete"💡 Tip: See examples/mcp_config_comprehensive.json for a complete configuration example with detailed comments and usage examples.
TaskFlow MCP enforces a specific workflow:
For AI assistants to consistently follow this workflow, see the example-system-prompt.md file for system prompts you can add to your assistant's instructions.
TaskFlow MCP exposes the following tools to AI assistants:
plan_taskRegister a new user request and plan its associated tasks (with optional subtasks).
{
"originalRequest": "Create a new website for my business",
"outputPath": "C:/Users/username/Documents/website-project-plan.md",
"dependencies": [
{
"name": "Node.js",
"version": ">=14.0.0",
"description": "JavaScript runtime"
},
{
"name": "npm",
"version": ">=6.0.0",
"description": "Package manager"
}
],
"notes": [
{
"title": "Package Manager Preference",
"content": "User prefers pnpm over npm for package management."
},
{
"title": "Design Guidelines",
"content": "Follow the company's brand guidelines for colors and typography."
}
],
"tasks": [
{
"title": "Design homepage",
"description": "Create a design for the homepage with logo, navigation, and hero section",
"dependencies": [
{
"name": "Figma",
"description": "Design tool"
}
],
"subtasks": [
{
"title": "Design logo",
"description": "Create a logo that represents the business brand"
},
{
"title": "Design navigation",
"description": "Create a user-friendly navigation menu"
}
]
},
{
"title": "Implement HTML/CSS",
"description": "Convert the design to HTML and CSS",
"dependencies": [
{
"name": "HTML5",
"description": "Markup language"
},
{
"name": "CSS3",
"description": "Styling language"
}
]
}
]
}
get_next_taskRetrieve the next pending task for a request.
{
"requestId": "req-1"
}
mark_task_doneMark a task as completed.
{
"requestId": "req-1",
"taskId": "task-1",
"completedDetails": "Created a modern design with a clean layout"
}
open_task_detailsGet details about a specific task.
{
"taskId": "task-1"
}
list_requestsList all requests in the system.
{}
add_tasks_to_requestAdd more tasks to an existing request.
{
"requestId": "req-1",
"tasks": [
{
"title": "Add contact form",
"description": "Create a contact form with validation"
}
]
}
update_taskUpdate a task's title or description.
{
"requestId": "req-1",
"taskId": "task-1",
"title": "Design responsive homepage",
"description": "Create a responsive design for the homepage"
}
delete_taskDelete a task from a request.
{
"requestId": "req-1",
"taskId": "task-1"
}
add_subtasksAdd subtasks to an existing task.
{
"requestId": "req-1",
"taskId": "task-1",
"subtasks": [
{
"title": "Design logo",
"description": "Create a logo that represents the business brand"
},
{
"title": "Design navigation",
"description": "Create a user-friendly navigation menu"
}
]
}
mark_subtask_doneMark a subtask as completed.
{
"requestId": "req-1",
"taskId": "task-1",
"subtaskId": "subtask-1"
}
update_subtaskUpdate a subtask's title or description.
{
"requestId": "req-1",
"taskId": "task-1",
"subtaskId": "subtask-1",
"title": "Design modern logo",
"description": "Create a modern logo that represents the business brand"
}
delete_subtaskDelete a subtask from a task.
{
"requestId": "req-1",
"taskId": "task-1",
"subtaskId": "subtask-1"
}
export_task_statusExport the current status of all tasks in a request to a file. It's recommended to use absolute paths for more reliable file creation.
{
"requestId": "req-1",
"outputPath": "C:/Users/username/Documents/task-status.md",
"format": "markdown"
}
add_noteAdd a note to a request.
{
"requestId": "req-1",
"title": "Package Manager Preference",
"content": "User prefers pnpm over npm for package management."
}
update_noteUpdate an existing note.
{
"requestId": "req-1",
"noteId": "note-1",
"title": "Package Manager Preference",
"content": "User prefers pnpm over npm and yarn for package management."
}
delete_noteDelete a note from a request.
{
"requestId": "req-1",
"noteId": "note-1"
}
add_dependencyAdd a dependency to a request or task.
{
"requestId": "req-1",
"taskId": "task-1",
"dependency": {
"name": "react",
"version": "^18.2.0",
"description": "JavaScript library for building user interfaces",
"url": "https://reactjs.org"
}
}
TaskFlow MCP now supports a global prompts system to enhance LLM focus and consistency across tasks. This addresses the need for custom instructions and task prefixes/suffixes as requested in user feedback.
get_promptsGet the current prompts configuration.
{}
Returns: Current prompts settings including instructions, taskPrefix, and taskSuffix.
set_promptsSet the global prompts configuration (replaces existing settings).
{
"instructions": "You are working on a React TypeScript project. Always follow the existing patterns and ensure type safety.",
"taskPrefix": "🎯 IMPORTANT: Review the project architecture before starting.",
"taskSuffix": "✅ Remember to run tests and ensure all imports are properly typed."
}
update_promptsUpdate specific parts of the prompts configuration without replacing everything.
{
"instructions": "Updated project context: Now using Next.js 14 with App Router.",
"taskPrefix": "🚀 NEW APPROACH: Consider server components first."
}
remove_promptsRemove the entire prompts configuration or specific fields.
{
"fields": ["taskPrefix", "taskSuffix"]
}
Leave empty to remove all prompts:
{}
When prompts are configured:
get_next_task or open_task_detailsExample task file with prompts:
prompts:
instructions: "Follow the company coding standards and review architecture docs"
taskPrefix: "📋 Before starting: Check dependencies and read recent changes"
taskSuffix: "🔍 After completion: Verify all tests pass and code is properly documented"
createdAt: "2024-03-15T10:30:00Z"
updatedAt: "2024-03-15T11:45:00Z"
requests:
- requestId: req-1
originalRequest: "Add user authentication"
# ... rest of tasks
TaskFlow MCP includes a comprehensive archiving system to keep your active tasks file clean by moving completed requests to a separate archive file. This addresses the issue of cluttered task files in large projects with many completed tasks.
Archive Configuration:
# Optional: Custom archive file path (defaults to tasks-archive.yaml in same directory as task file)
ARCHIVE_FILE_PATH=/path/to/custom-archive.yaml
# Optional: Archive mode (manual or auto-on-complete, defaults to manual)
ARCHIVE_MODE=manual
archive_completed_requestsArchive completed requests to keep the active tasks file clean.
{
"requestIds": ["req-1", "req-2"]
}
Archive all completed requests:
{}
list_archived_requestsList archived requests with optional search and filtering.
{
"searchTerm": "website project",
"limit": 10
}
restore_archived_requestRestore an archived request back to active tasks.
{
"requestId": "req-1"
}
Archived requests are stored in the same format (JSON/YAML) as your task file:
archiveInfo:
createdAt: "2024-03-15T10:00:00Z"
lastArchivedAt: "2024-03-15T15:30:00Z"
totalArchivedRequests: 5
version: "1.0.0"
archivedRequests:
- requestId: req-1
originalRequestId: req-1
originalRequest: "Build user authentication system"
archivedAt: "2024-03-15T15:30:00Z"
completedAt: "2024-03-15T15:25:00Z"
tasks:
- # ... completed tasks
# ... other request data
archive_completed_requests to move them to archivelist_archived_requests to view archived workrestore_archived_request to bring back archived requestsBenefits:
For more detailed information about the project architecture and implementation, see the OVERVIEW.md file.
This project is licensed under the MIT License - see the LICENSE file for details.
Contributions are welcome! Please see the CONTRIBUTING.md file for guidelines.
See the CHANGELOG.md file for a history of changes to this project.
Made with ❤️ by Pink Pixel
A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow wit
ภาพรวม
A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow with user approval steps.
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Taskflow ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-27 A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow with user approval steps.