get_project_infoLABSCO SUMMARY
The interesting tools are the ones about failure, not about tasks.
Task tracking is the visible layer; detect_failure_patterns and check_pattern_risk are what make it more than a Kanban board with an API — the system flags an approach that has burned you before, using its own recorded history. rollback_task and the snapshot tools follow the same instinct. It is a large surface with a database dependency, so treat setup as a real step.
What it is
Orchestro sits between product intent and code. Write a user story and it decomposes it into technical tasks; from there it tracks dependencies and conflicts, enriches the implementation prompt, records what worked, and keeps a full history — with a live Kanban dashboard for people who do not read code.
What you get
- Tasks —
create_task,list_tasks,update_task,delete_task,get_execution_orderfor a topological sort by dependency,safe_delete_tasks_by_status - Execution flow —
prepare_task_for_executiongenerates the codebase analysis prompt,save_task_analysisstores the result,get_execution_promptreturns enriched implementation context - User stories —
decompose_storyturns a story into tasks with analysis on by default, plusget_user_stories,get_tasks_by_user_story,get_user_story_health - Dependencies and conflicts —
save_dependencies,get_task_dependency_graph,get_resource_usage,get_task_conflictsto catch two tasks touching the same files - Knowledge and learning —
list_templates,list_patterns,list_learnings,render_template,get_relevant_knowledge,add_feedback,get_similar_learnings,get_top_patterns,get_trending_patterns,get_pattern_stats,detect_failure_patterns,check_pattern_risk - Project configuration — tech stack, guardian sub-agents including
sync_claude_code_agentsandsuggest_agents_for_task, MCP tool registration withsuggest_tools_for_task, guidelines and code patterns - History —
get_task_history,get_status_history,get_decisions,record_decision,get_code_changes,get_guardian_interventions,get_task_snapshotat a timestamp, androllback_taskto restore a previous state
Requirements
Node.js 18+ and a Supabase project (the free tier is enough). Register npx -y @khaoss85/orchestro@latest in your Claude Code config with DATABASE_URL set to the Supabase connection string; SUPABASE_URL and SUPABASE_SERVICE_KEY come from the project's API settings and the service key must stay secret. Apply the schema with the migration script before first use. The real-time dashboard runs over Socket.io. Package version 2.1.0. MIT.
Setup effort
One command plus a key — npx @khaoss85/orchestro@latest, then supply credentials
USE CASES
01
Turning a story into work you can start
Decompose the story into technical tasks with analysis, then get the order they should be done in.
02
Stopping two tasks colliding
Record what each task touches, then check for conflicting resource usage before both are picked up.
03
Not repeating an approach that failed
Check the risk of a pattern before using it, and read the similar learnings behind that verdict.
04
Explaining what changed and why
Pull the task's event timeline, the decisions recorded against it and the code changes logged.
05
Undoing a bad step
Read the task snapshot from before the change, then roll the task back to it.
60 tools
Listed in project docs. Your client may show a different list.
get_project_configurationinitialize_project_configurationcreate_tasklist_tasksupdate_taskdelete_taskget_task_contextget_execution_ordersafe_delete_tasks_by_statusprepare_task_for_executionsave_task_analysisget_execution_promptdecompose_storyget_user_storiesget_tasks_by_user_storyget_user_story_healthsave_dependenciesget_task_dependency_graphget_resource_usageget_task_conflictslist_templateslist_patternslist_learningsrender_templateget_relevant_knowledgeadd_feedbackget_similar_learningsget_top_patternsget_trending_patternsget_pattern_statsdetect_failure_patternscheck_pattern_riskadd_tech_stackupdate_tech_stackremove_tech_stackadd_sub_agentupdate_sub_agentsync_claude_code_agentsread_claude_code_agentssuggest_agents_for_taskupdate_agent_prompt_templatesadd_mcp_toolupdate_mcp_toolsuggest_tools_for_taskadd_guidelineadd_code_patternget_task_historyget_status_historyget_decisionsget_guardian_interventionsget_code_changesrecord_decisionrecord_code_changerecord_guardian_interventionrecord_status_transitionget_iteration_countget_task_snapshotrollback_taskget_task_statsBEFORE YOU INSTALL
What to know first
Tools you get
60 tools named in the project's documentation.
Requires
- npx on PATH
- SUPABASE_SERVICE_KEY in your environment
- ANTHROPIC_API_KEY in your environment
- DATABASE_URL in your environment
- SUPABASE_URL in your environment
INSTALLATION
Connect your client
Server setup
Setup
Create the database schema in your Supabase project once, from a clone of the repository.
TERMINAL
git clone https://github.com/khaoss85/mcp-orchestro.git
cd mcp-orchestro
npm install
export DATABASE_URL="<YOUR_DATABASE_URL>"
npm run migratenpx
TERMINAL
npx @khaoss85/orchestro@latestMCP Clients
Claude Code, Claude Desktop
JSON
{
"mcpServers": {
"orchestro": {
"command": "npx",
"args": [
"-y",
"@khaoss85/orchestro@latest"
],
"env": {
"DATABASE_URL": "<YOUR_DATABASE_URL>"
}
}
}
}The configuration on this page does not set SUPABASE_SERVICE_KEY, ANTHROPIC_API_KEY and SUPABASE_URL; the project's instructions set them with an export line. An app opened from its icon or dock does not see variables exported in a terminal, so to supply them, use the block's "env" section.
Claude Code — plugin
CLAUDE CODE — PLUGIN · IN CLIENT
/plugin marketplace add khaoss85/mcp-orchestro
/plugin install orchestro-suite@orchestro-marketplace
