MCP Task Manager
by chriscarrollsmith
MCP Task Manager is a Model Context Protocol (MCP) server for AI task management. This tool helps AI assistants handle multi-step tasks in a structured way, with optional user approval checkpoints.
Last updated: N/A
What is MCP Task Manager?
MCP Task Manager is an MCP server designed to manage multi-step tasks for AI assistants. It provides a structured way to plan, track, and execute tasks, with optional user approval checkpoints at various stages.
How to use MCP Task Manager?
To use the Task Manager, configure it in your MCP client (e.g., Claude Desktop, Cursor) with the provided JSON configuration. Use the CLI for task inspection, management, and approval. The AI agent creates projects and tasks, marks tasks as done, and the user approves them via the CLI. Environment variables for LLM providers (OpenAI, Google Gemini, Deepseek) can be set to enable project plan generation.
Key features of MCP Task Manager
Task planning with multiple steps
Progress tracking
User approval of completed tasks
Project completion approval
Task details visualization
Task status state management
Enhanced CLI for task inspection and management
Use cases of MCP Task Manager
Managing complex projects with multiple dependencies
Automating workflows that require human oversight
Integrating AI agents into existing task management systems
Providing a structured framework for AI task execution
FAQ from MCP Task Manager
How do I install the CLI?
How do I install the CLI?
Install the package globally using npm install -g taskqueue-mcp or run with npx --package=taskqueue-mcp taskqueue --help.
How do I configure the Task Manager in my MCP client?
How do I configure the Task Manager in my MCP client?
Use the provided JSON configuration snippet in your MCP client settings.
How do I approve tasks?
How do I approve tasks?
Use the CLI command npx taskqueue approve-task -- <projectId> <taskId>.
Where is the task data stored?
Where is the task data stored?
By default, task data is stored in a JSON file in a platform-specific location (Linux: ~/.local/share/taskqueue-mcp/tasks.json, macOS: ~/Library/Application Support/taskqueue-mcp/tasks.json, Windows: %APPDATA%\taskqueue-mcp\tasks.json).
Can I use a custom file path for storing task data?
Can I use a custom file path for storing task data?
Yes, but it is not recommended. If you do want to use a custom path, you can set the TASK_MANAGER_FILE_PATH environment variable in your MCP client configuration and in your shell before running the CLI.