SystemPrompt MCP TaskChecker

Model Context Protocol (MCP) server for intelligent task management, evaluation scoring, and session-based workflow tracking. Seamlessly integrates with AI assistants to provide structured task orchestration, real-time progress monitoring, and comprehensive evaluation metrics.

typescript

2

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can deploy and use the SystemPrompt MCP TaskChecker to manage complex AI-assisted tasks with real-time progress, structured evaluation, and secure, session-based workflows. This MCP server orchestrates tasks, tracks status, evaluates outcomes, and provides a scalable interface for AI assistants to collaborate on multi-step processes.

How to use

You connect an MCP client to the SystemPrompt MCP TaskChecker to drive task-based work streams. Use an HTTP MCP endpoint for remote integration or run the MCP server locally as a stdio process. Typical usage patterns include creating a new task list with initial tasks, updating individual tasks as work progresses, and querying the status of an entire task list to monitor overall progress. The system automatically tracks status transitions (pending → in_progress → completed) and records evaluation scores to measure completion quality. You can define acceptance criteria for each task to ensure clear completion requirements and keep data consistent when you modify any task property.

How to install

Prerequisites: Node.js 18.0.0 or higher, npm (latest stable), and TypeScript (included in devDependencies). Prepare your environment by ensuring these tools are installed and accessible from your shell.

Step-by-step setup and run flow you can follow directly:

Clone the project locally to your development machine or server.
Install dependencies to fetch all required packages.
Build the project so the TypeScript sources are compiled to runnable JavaScript.
Start the MCP TaskChecker server and begin handling MCP interactions.

Available tools

create_tasklist

Creates a new task list for the current session with optional initial tasks, returning the list ID, session ID, and the created tasks.

update_task

Updates specific task properties such as title, status, acceptance criteria, and evaluation score for a given task within a task list.

get_status

Retrieves current status for all tasks in a list or a specific task by its ID.