TaskFlow MCP
TaskFlow MCP🔄✅
用于与 AI 助手一起规划和执行任务的任务管理模型上下文协议 (MCP) 服务器。
🌟 概述
TaskFlow MCP 是一款专用服务器,可帮助 AI 助手将用户请求分解为可管理的任务并跟踪其完成情况。它强制执行结构化的工作流,并包含用户审批步骤,以确保任务得到正确跟踪,并保持用户对流程的控制。
Related MCP server: Tiny TODO MCP
✨ 特点
📋任务规划:将复杂的请求分解为可管理的任务
🔍子任务:将任务划分为更小、更易于管理的子任务
📊进度跟踪:使用可视化进度表跟踪任务、子任务和请求的状态
👍用户批准:强制用户批准步骤以确保质量和控制
💾持久性:将任务和请求保存到磁盘,以便在会话之间持久化
🔄灵活管理:根据需要添加、更新或删除任务和子任务
📝详细报告:查看任务详细信息和进度表
📤导出选项:以 Markdown、JSON 或 HTML 格式导出任务计划和状态报告
📦依赖关系:使用版本信息跟踪项目和任务级依赖关系
📌注释:为重要信息和偏好添加项目级注释
🚀 安装
全局安装
npm install -g @pinkpixel/taskflow-mcp本地安装
npm install @pinkpixel/taskflow-mcp🛠️ 使用方法
启动服务器
如果全局安装:
taskflow-mcp如果本地安装:
npx taskflow-mcp配置
默认情况下,TaskFlow MCP 将任务保存到~/Documents/tasks.json 。您可以通过设置TASK_MANAGER_FILE_PATH环境变量来更改此设置:
TASK_MANAGER_FILE_PATH=/path/to/tasks.json taskflow-mcpMCP 配置
要将 TaskFlow MCP 与 AI 助手配合使用,您需要配置 MCP 客户端以使用服务器。创建一个包含以下内容的mcp_config.json文件:
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": ["-y", "@pinkpixel/taskflow-mcp"],
"env": {
"TASK_MANAGER_FILE_PATH": "/path/to/tasks.json"
}
}
}
}🔄 工作流程
TaskFlow MCP 强制执行特定的工作流程:
计划任务:将用户请求分解为任务(带有可选的子任务)
获取下一个任务:检索下一个待处理的任务
完成子任务:如果任务有子任务,则在将任务标记为完成之前完成每个子任务
标记任务完成:将任务标记为已完成(需要先完成所有子任务)
等待批准:等待用户批准已完成的任务
重复:继续下一个任务,直到所有任务完成
最终批准:获得用户对整个请求的批准
为了让 AI 助手始终遵循此工作流程,请参阅example-system-prompt.md文件,了解可以添加到助手指令中的系统提示。
🧰 可用工具
TaskFlow MCP 向 AI 助手公开了以下工具:
plan_task
注册新的用户请求并计划其相关任务(带有可选的子任务)。
{
"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_task
检索请求的下一个待处理任务。
{
"requestId": "req-1"
}mark_task_done
将任务标记为已完成。
{
"requestId": "req-1",
"taskId": "task-1",
"completedDetails": "Created a modern design with a clean layout"
}approve_task_completion
批准已完成的任务。
{
"requestId": "req-1",
"taskId": "task-1"
}approve_request_completion
批准整个请求并认为其已完成。
{
"requestId": "req-1"
}open_task_details
获取有关特定任务的详细信息。
{
"taskId": "task-1"
}list_requests
列出系统中的所有请求。
{}add_tasks_to_request
向现有请求添加更多任务。
{
"requestId": "req-1",
"tasks": [
{
"title": "Add contact form",
"description": "Create a contact form with validation"
}
]
}update_task
更新任务的标题或描述。
{
"requestId": "req-1",
"taskId": "task-1",
"title": "Design responsive homepage",
"description": "Create a responsive design for the homepage"
}delete_task
从请求中删除任务。
{
"requestId": "req-1",
"taskId": "task-1"
}add_subtasks
将子任务添加到现有任务。
{
"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_done
将子任务标记为已完成。
{
"requestId": "req-1",
"taskId": "task-1",
"subtaskId": "subtask-1"
}update_subtask
更新子任务的标题或描述。
{
"requestId": "req-1",
"taskId": "task-1",
"subtaskId": "subtask-1",
"title": "Design modern logo",
"description": "Create a modern logo that represents the business brand"
}delete_subtask
从任务中删除子任务。
{
"requestId": "req-1",
"taskId": "task-1",
"subtaskId": "subtask-1"
}export_task_status
将请求中所有任务的当前状态导出到文件。建议使用绝对路径,以便更可靠地创建文件。
{
"requestId": "req-1",
"outputPath": "C:/Users/username/Documents/task-status.md",
"format": "markdown"
}add_note
为请求添加注释。
{
"requestId": "req-1",
"title": "Package Manager Preference",
"content": "User prefers pnpm over npm for package management."
}update_note
更新现有注释。
{
"requestId": "req-1",
"noteId": "note-1",
"title": "Package Manager Preference",
"content": "User prefers pnpm over npm and yarn for package management."
}delete_note
从请求中删除注释。
{
"requestId": "req-1",
"noteId": "note-1"
}add_dependency
向请求或任务添加依赖项。
{
"requestId": "req-1",
"taskId": "task-1",
"dependency": {
"name": "react",
"version": "^18.2.0",
"description": "JavaScript library for building user interfaces",
"url": "https://reactjs.org"
}
}📚 文档
有关项目架构和实施的更多详细信息,请参阅OVERVIEW.md文件。
📝 许可证
该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅LICENSE文件。
🤝 贡献
欢迎贡献!请参阅CONTRIBUTING.md文件以获取相关指南。
📜 更新日志
请参阅CHANGELOG.md文件了解该项目的变更历史记录。
🙏 致谢
使用模型上下文协议(MCP)构建
由Pink Pixel创建
由 Pink Pixel 用❤️制作
Maintenance
Related MCP Servers
- AlicenseBqualityDmaintenanceA server for task orchestration and coordination, facilitating task management with dependencies, multi-instance collaboration, and persistent task tracking.7225MIT
- Flicense-qualityDmaintenanceA Model Context Protocol server that provides persistent task management capabilities for AI assistants, allowing them to create, update, and track tasks beyond their usual context limitations.5
- -licenseAquality-maintenanceA task management Model Context Protocol server that helps break down user requests into manageable tasks with subtasks, dependencies, and notes, while enforcing a structured workflow with user approval steps.173510
- Alicense-qualityDmaintenanceA task management system for LLM-based agents that stores all tasks in a single tree, available immediately after the server starts.4Apache 2.0
Related MCP Connectors
Automate tasks, processes, and approvals with AI.
Project management MCP for AI agents with safe task reads and writes.
The Teamwork.com official MCP server helps teams efficiently manage client projects with AI.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pinkpixel-dev/taskflow-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server