TaskFlow
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.
What is TaskFlow?
TaskFlow is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 ...
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.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A task management Model Context Protocol (MCP) server that h
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx taskflow-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use TaskFlow
TaskFlow MCP is a task management server for the Model Context Protocol that helps AI assistants decompose complex user requests into structured plans with tasks, subtasks, dependencies, and notes, then enforce a step-by-step approval workflow so users stay in control. It persists task state to disk in YAML or JSON format, supports exporting plans to Markdown, JSON, or HTML, and includes a full archive system for completed work. AI assistants like Claude use TaskFlow's tools to plan work, retrieve the next actionable task, mark items complete only after user confirmation, and track project-level dependencies — preventing runaway autonomous execution.
Prerequisites
- Node.js 18 or higher
- An MCP-compatible client such as Claude Desktop or Cursor
- Write access to a directory for storing the tasks file (YAML or JSON)
Install TaskFlow MCP globally
Install the @pinkpixel/taskflow-mcp package globally so it is available as a command on your PATH.
npm install -g @pinkpixel/taskflow-mcpChoose a tasks file location
Decide where TaskFlow will persist your tasks. The default is tasks.yaml in the working directory. Set TASK_MANAGER_FILE_PATH to use a custom location.
# Use a fixed absolute path (recommended):
export TASK_MANAGER_FILE_PATH=/home/user/projects/my-tasks.yaml
# Or let it default to tasks.yaml in the current directoryTest the server manually
Verify the server starts without errors by running it directly.
taskflow-mcpConfigure your MCP client
Add TaskFlow to your Claude Desktop or Cursor MCP configuration, setting the TASK_MANAGER_FILE_PATH environment variable to your chosen path.
Restart your MCP client
Restart Claude Desktop or your MCP client to pick up the new server configuration. TaskFlow should appear in the connected servers list.
TaskFlow Examples
Client configuration
Claude Desktop configuration for TaskFlow MCP with a fixed tasks file path and manual archive mode.
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": ["-y", "@pinkpixel/taskflow-mcp"],
"env": {
"TASK_MANAGER_FILE_PATH": "/home/user/projects/tasks.yaml",
"ARCHIVE_FILE_PATH": "/home/user/projects/tasks-archive.yaml",
"ARCHIVE_MODE": "manual"
}
}
}
}Prompts to try
Example prompts that trigger TaskFlow's planning and approval workflow in Claude.
- "Break down the task of migrating our database to PostgreSQL into a step-by-step plan with subtasks"
- "What is the next pending task I should work on?"
- "Mark the 'Set up connection pooling' subtask as complete"
- "Show me a progress table for all tasks in the database migration project"
- "Export the current task plan as a Markdown checklist"
- "Archive all completed requests to clean up the active task list"Troubleshooting TaskFlow
Tasks are not persisted between sessions
Set TASK_MANAGER_FILE_PATH to an absolute path in the MCP client config env block. Without this, tasks.yaml defaults to the working directory at process start, which may change between sessions.
Claude marks tasks as done without asking for user confirmation
TaskFlow enforces the approval workflow through its tool contracts, but the AI assistant must follow the workflow. Add a system prompt instructing Claude to always call get_next_task, complete work, then wait for explicit user confirmation before proceeding. See example-system-prompt.md in the repository.
Server fails to start with YAML parse errors on an existing tasks file
TaskFlow supports both .yaml and .json extensions, detected automatically. If you have a legacy JSON file, either rename it to .json and update TASK_MANAGER_FILE_PATH, or migrate to YAML by changing the file extension to .yaml (the schema is compatible).
Frequently Asked Questions about TaskFlow
What is TaskFlow?
TaskFlow is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install TaskFlow?
Follow the installation instructions on the TaskFlow GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with TaskFlow?
TaskFlow works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is TaskFlow free to use?
Yes, TaskFlow is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
TaskFlow Alternatives — Similar Business Applications Servers
Looking for alternatives to TaskFlow? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up TaskFlow in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use TaskFlow?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.