systemprompt -taskchecker

The SystemPrompt MCP TaskChecker is an enterprise-grade MCP server that provides structured task orchestration, real-time workflow tracking, and a robust evaluation system for AI-assisted task management. It exposes MCP endpoints to create and manage task lists, update individual tasks (including status and evaluation), and fetch current task status across sessions. Use it to coordinate tasks between AI assistants (like Claude or GPT) and your human users, track progress in real time, and record 0-100 evaluation scores for completed tasks. The server is built with TypeScript, adheres to MCP 2025-03-26 standards, and supports streamable HTTP transport for scalable interactions.

Key capabilities include:

• Intelligent Task Orchestration: create task lists with initial tasks, monitor dynamic status transitions (pending -> in_progress -> completed), and enforce clear acceptance criteria.
• Advanced Evaluation System: assign 0-100 quality scores, track metrics, and maintain historical evaluation data for continuous improvement.
• Enterprise Session Management: stateful sessions with automatic cleanup and concurrent session support, plus built-in security validations.
• Production-Grade Architecture: type-safe TypeScript code, structured error handling, and robust logging for production deployments.

To use, start the server and send MCP calls via the Tools API. Use create_tasklist to initialize a session with tasks, update_task to modify status or evaluation, and get_status to retrieve current task states. The provided usage examples in the README demonstrate the exact JSON payloads for common operations.

Prerequisites

• Node.js 18.x or higher
• npm (latest stable)
• Git

Step-by-step installation

1. Clone the repository git clone https://github.com/your-org/systemprompt-mcp-taskchecker.git cd systemprompt-mcp-taskchecker

2. Install dependencies npm install

3. Build the project npm run build

4. Start the server npm start

Optional for development

• Run in development mode with hot reload: npm run dev

Docker deployment (optional)

• Build Docker image: npm run docker:build
• Run in container: npm run docker:run

Prerequisites for Docker (if using Docker):

• Docker installed on your system
• Sufficient CPU/RAM for containerized workloads

Environment variables and configuration tips:

• PORT: The HTTP port the MCP server will listen on (default 3000).
• NODE_ENV: Set to production for production-grade behavior.
• API_KEY or other integration keys: Add any external service credentials as needed by your deployment.
• Ensure MCP 2025-03-26 compatibility by keeping dependencies up to date and following the README’s build/start workflow.

Common issues:

• If npm start fails due to build errors, run npm run build to regenerate dist files.
• When running in Docker, ensure volume mounts and environment variables are correctly passed to the container.
• For verification, exercise the provided usage examples (create_tasklist, update_task, get_status) to confirm endpoints respond as expected.