Taskqueue

Name: Taskqueue
Author: chriscarrollsmith

@chriscarrollsmith

Repository

About Taskqueue

No overview available yet

#taskqueue #task-manager #ai-assistant

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "taskqueue": {
      "command": "npx",
      "args": [
        "-y",
        "taskqueue-mcp"
      ]
    }
  }
}

Tools

List all projects in the system and their basic information (ID, initial prompt, task counts), optionally filtered by state (open, pending_approval, completed, all).

Read all information for a given project, by its ID, including its tasks' statuses.

Create a new project with an initial prompt and a list of tasks. This is typically the first step in any workflow.

Delete a project and all its associated tasks.

Add new tasks to an existing project.

Mark a project as complete. Can only be called when all tasks are both done and approved. This is typically the last step in a project workflow.

Use an LLM to generate a project plan and tasks from a prompt. The LLM will analyze the prompt and any attached files to create a structured project plan.

List all tasks, optionally filtered by project ID and/or state (open, pending_approval, completed, all). Tasks may include tool and rule recommendations to guide their completion.

Get details of a specific task by its ID. The task may include toolRecommendations and ruleRecommendations fields that should be used to guide task completion.

Create a new task within an existing project. You can optionally include tool and rule recommendations to guide task completion.

Modify a task's properties. Note: (1) completedDetails are required when setting status to 'done', (2) approved tasks cannot be modified, (3) status must follow valid transitions: not started → in progress → done. You can also update tool and rule recommendations to guide task completion.

Remove a task from a project.

Approve a completed task. Tasks must be marked as 'done' with completedDetails before approval. Note: This is a CLI-only operation that requires human intervention.

Get the next task to be done in a project. Returns the first non-approved task in sequence, regardless of status. The task may include toolRecommendations and ruleRecommendations fields that should be used to guide task completion.

Overview

What is Taskqueue?

Taskqueue is a Model Context Protocol (MCP) server for AI task management. It helps AI assistants handle multi-step tasks in a structured way, with user approval checkpoints. It is designed for use with MCP clients like Claude Desktop or Cursor.

How to use Taskqueue?

Configure the tool in your MCP client using the command npx -y taskqueue-mcp. Optionally set the TASK_MANAGER_FILE_PATH environment variable to specify a custom storage location. Use the CLI utility (npx task-manager-cli --help) for task approval and listing.

Key features of Taskqueue

Task planning with multiple steps
Progress tracking through task statuses
User approval of completed tasks
Project completion approval
Task details visualization
CLI for task inspection and management
Enforced status transition rules

Use cases of Taskqueue

AI assistant managing a multi-step project (e.g., website creation)
Structured task breakdown with human-in-the-loop approval
Tracking and documenting completion of subtasks
Project finalization after all tasks are approved

FAQ from Taskqueue

What runtime does Taskqueue require?

Taskqueue requires Node.js to run. It is executed via npx, which downloads and runs the taskqueue-mcp package.

Where does Taskqueue store its data?

Data is stored in a JSON file in a platform-specific default location: ~/.local/share/taskqueue-mcp/tasks.json (Linux), ~/Library/Application Support/taskqueue-mcp/tasks.json (macOS), or %APPDATA%\taskqueue-mcp\tasks.json (Windows). A custom path can be set via the TASK_MANAGER_FILE_PATH environment variable.

What are the valid task status transitions?

Tasks follow a workflow: not started → in progress → done. You can move back from in progress to not started, and from done to in progress if additional work is needed. Approved tasks cannot be modified.

How does user approval work?

Task approval is controlled exclusively by the human user through the CLI command npm run approve-task -- <projectId> <taskId>. Tasks must be marked as "done" with completed details before they can be approved (unless using the --force option).

What authentication or transport does Taskqueue use?

The README does not specify authentication or transport details. It uses the standard MCP protocol over stdio (implied by the client configuration). No authentication mechanism is mentioned.