What is TaskFlow MCP?

TaskFlow MCP is a task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. It enforces a structured workflow with user approval steps.

How does TaskFlow MCP integrate with AI assistants?

TaskFlow MCP exposes a set of tools that AI assistants can use to plan, execute, and track tasks. These tools include plan_task, get_next_task, mark_task_done, and others, allowing AI assistants to interact with the server to manage tasks efficiently.

What is the Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). An MCP server acts as a bridge, enabling AI models to access and interact with external data sources and tools.

What are the key features of TaskFlow MCP?

Key features include task planning, subtasks, progress tracking, user approval, persistence, flexible management, detailed reporting, export options, dependencies tracking, and notes.

How do I install TaskFlow MCP?

You can install TaskFlow MCP globally using npm install -g @pinkpixel/taskflow-mcp or locally using npm install @pinkpixel/taskflow-mcp.

How do I start the TaskFlow MCP server?

If installed globally, use the command taskflow-mcp. If installed locally, use npx taskflow-mcp.

How do I configure TaskFlow MCP?

By default, TaskFlow MCP saves tasks to ~/Documents/tasks.json. You can change this by setting the TASK_MANAGER_FILE_PATH environment variable.

How do I use TaskFlow MCP with AI assistants?

Create an mcp_config.json file with the necessary configuration details for your MCP client to connect to the TaskFlow MCP server.

What workflow does TaskFlow MCP enforce?

TaskFlow MCP enforces a structured workflow including planning tasks, retrieving the next pending task, completing subtasks, marking tasks as done, waiting for approval, and repeating the process until all tasks are complete, followed by final approval of the entire request.

What is UBOS and how does TaskFlow MCP fit in?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. The TaskFlow MCP server on the UBOS Asset Marketplace provides a robust solution for structuring, tracking, and executing tasks within AI workflows, enhancing the capabilities of AI Agents.

What tools are available in TaskFlow MCP?

Available tools include plan_task, get_next_task, mark_task_done, approve_task_completion, approve_request_completion, open_task_details, list_requests, add_tasks_to_request, update_task, delete_task, add_subtasks, mark_subtask_done, update_subtask, delete_subtask, export_task_status, add_note, update_note, and delete_note, add_dependency.

How can I contribute to TaskFlow MCP?

Contributions are welcome! Please see the CONTRIBUTING.md file for guidelines.