mcp-task-orchestrator

Overview

The MCP Task Orchestrator is a comprehensive Python-based server that transforms AI-assisted development through intelligent task decomposition and execution. It employs specialist AI roles (Architect, Implementer, Tester, Reviewer, etc.) to ensure each aspect of a project receives domain-specific expertise. Built with Clean Architecture principles, it automatically detects project structures and maintains persistent memory of all decisions and implementations. The server includes workspace intelligence, artifact management, and a comprehensive template system with 13 tools for reusable task templates.

Try asking AI

After installing, here are 8 things you can ask your AI assistant:

• orchestrator_initialize_sessionorchestrator_initialize_session(working_directory)

  Start a new orchestration session with optional working directory

  Try:Initialize a new orchestration sessionTry:Initialize a new orchestration session for my project at /home/user/project
• orchestrator_plan_taskorchestrator_plan_task(task_description)

  Create a structured breakdown of tasks from a request

  Try:Plan a Python script for processing CSV filesTry:Break down the requirements for an e-commerce website
• orchestrator_execute_taskorchestrator_execute_task(task_id)

  Execute a specific task with specialist role context

  Try:Execute task 3 with Implementer role contextTry:Run the API implementation task
• orchestrator_complete_taskorchestrator_complete_task(task_id, artifacts)

  Mark a task as complete with associated artifacts

  Try:Complete task 5 with the test artifactsTry:Finish the documentation task with the generated PDF
• orchestrator_synthesize_resultsorchestrator_synthesize_results(project_id)

  Combine all task results into a comprehensive solution

  Try:Synthesize the results for my projectTry:Create a comprehensive report from all completed tasks
• orchestrator_get_statusorchestrator_get_status(project_id)

  Check the progress and status of the orchestration session

  Try:What's the current status of my project?Try:Show me the progress of all tasks
• orchestrator_maintenance_coordinatororchestrator_maintenance_coordinator(action_type)

  Perform automated cleanup and optimization of sessions

  Try:Run the maintenance coordinator to cleanup old sessionsTry:Optimize the database and archive stale tasks

Comparable tools

Installation

# Clone and run the universal installer
git clone https://github.com/EchoingVesper/mcp-task-orchestrator.git
cd mcp-task-orchestrator
python install.py

pip install mcp-task-orchestrator

{
  "mcpServers": {
    "task-orchestrator": {
      "command": "python",
      "args": ["-m", "mcp_task_orchestrator.server"]
    }
  }
}

FAQ

Which MCP clients are supported?

The server fully supports Claude Desktop, Cursor IDE, Windsurf, and VS Code with extensions. It has partial support for Continue.dev and Cline with ongoing development.

How does the persistent memory work?

The server uses SQLite to store all task decisions, implementations, and artifacts. It provides automatic recovery and archival of tasks older than 24 hours, ensuring no context is ever lost.

Can I customize the specialist AI roles?

Yes. You can edit `.task_orchestrator/roles/project_roles.yaml` to create project-specific specialists with custom expertise, approach guidelines, and role definitions.

Compare mcp-task-orchestrator with