orchestrator_initialize_sessionLABSCO SUMMARY
The maintenance coordinator is the part that keeps this from rotting.
Any system that records every decision accumulates dead tasks, and this one archives work older than 24 hours, validates the task hierarchy and reports health rather than waiting for the store to become unusable. The specialist roles are worth customising early — the built-in set is generic, and a project-specific role file is where the orchestration starts producing output shaped like your codebase.
What it is
An MCP server that turns one large request into an orchestrated sequence of specialist roles, then documents what each one did. It detects your project structure and saves artifacts where they belong, keeps the decisions and implementations from previous sessions so context is not lost, and includes a maintenance pass that archives stale work and keeps the store from bloating.
What you get
- A session started against a working directory, then a task broken into a plan —
orchestrator_initialize_session,orchestrator_plan_task - Each subtask executed with a specialist role's context and completed with its artifacts attached, then combined into a result —
orchestrator_execute_task,orchestrator_complete_task,orchestrator_synthesize_results - Progress readable at any point —
orchestrator_get_status - Automated upkeep: stale tasks over 24 hours detected and archived, database bloat prevented, task hierarchies validated, handovers prepared and system health reported —
orchestrator_maintenance_coordinator - Built-in specialist roles — architect, implementer, tester, reviewer, documenter — plus project-specific ones you define in
.task_orchestrator/roles/project_roles.yaml, created automatically when you start a session in a directory - A template system for reusable task templates — create, load, validate and instantiate them, or install the bundled examples and default library
- Workspace awareness: project structure detected so artifacts land in the right place rather than the current directory
Requirements
No account and no key. Python 3.8+ and pip install mcp-task-orchestrator, then add it to your MCP client's configuration; the PyPI release is mcp-task-orchestrator 1.8.0, with mcp-task-orchestrator and mcp-task-orchestrator-cli entry points. Custom specialist roles are a YAML file in .task_orchestrator/roles/ inside the project, written the first time you start an orchestration session there.
Setup effort
One command — pip install mcp-task-orchestrator
USE CASES
01
Getting structured work instead of one long answer
Initialise a session and plan the task, so it arrives as specialist steps with their own artifacts rather than a single wall of code.
02
Keeping decisions after the session ends
Complete each subtask with its artifacts and synthesise the results, so the reasoning survives as documentation rather than scrollback.
03
Handing a project to someone else
Run the maintenance coordinator's handover preparation so context transitions come with a validated task hierarchy.
04
Teaching it your own review standards
Define a project-specific specialist in the roles file with its expertise and approach, and it becomes one of the roles the orchestrator assigns.
28 tools
Listed in project docs. Your client may show a different list.
orchestrator_get_statusorchestrator_plan_taskorchestrator_execute_taskorchestrator_complete_taskorchestrator_update_taskorchestrator_query_tasksorchestrator_delete_taskorchestrator_cancel_taskorchestrator_synthesize_resultstemplate_createtemplate_listtemplate_loadtemplate_instantiatetemplate_validatetemplate_deletetemplate_infotemplate_install_examplestemplate_install_default_librarytemplate_get_installation_statustemplate_validate_alltemplate_uninstallorchestrator_health_checkorchestrator_restart_serverorchestrator_shutdown_prepareorchestrator_reconnect_testorchestrator_restart_statusorchestrator_maintenance_coordinatorBEFORE YOU INSTALL
What to know first
Tools you get
28 tools named in the project's documentation.
Requires
- pip on PATH
- Python 3.8+
Where it runs
All 3 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install mcp-task-orchestratorMCP Clients
Claude Desktop, Cursor, Windsurf
JSON
{
"mcpServers": {
"mcp-task-orchestrator": {
"command": "python",
"args": [
"-m",
"mcp_task_orchestrator.server"
],
"env": {
"MCP_TASK_ORCHESTRATOR_USE_DI": "true"
}
}
}
}
