Skip to content
Agentmart
Submit a tool

Orchestro

Your AI Development Conductor - 60 MCP tools for intelligent task orchestration

Connector by khaoss85 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/khaoss85-orchestro

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Your AI Development Conductor - 60 MCP tools for intelligent task orchestration

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
33 read · 20 write · 5 delete · 4 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 62

Read from the source code; the running server may list different tools.

Read 33 · Look things up without changing anything.

  • check_pattern_risk
  • detect_failure_patterns
  • get_code_changes
  • get_decisions
  • get_execution_order
  • get_execution_prompt
  • get_guardian_interventions
  • get_iteration_count
  • get_pattern_stats
  • get_project_configuration
  • get_project_info
  • get_relevant_knowledge
Show 21 more tools
  • get_resource_usage
  • get_similar_learnings
  • get_status_history
  • get_task_conflicts
  • get_task_context
  • get_task_dependency_graph
  • get_task_history
  • get_task_snapshot
  • get_task_stats
  • get_tasks_by_user_story
  • get_top_patterns
  • get_trending_patterns
  • get_user_stories
  • get_user_story_health
  • list_learnings
  • list_patterns
  • list_tasks
  • list_templates
  • read_claude_code_agents
  • suggest_agents_for_task
  • suggest_tools_for_task

Write 20 · Create, change, send or run things.

  • add_code_pattern
  • add_feedback
  • add_guideline
  • add_mcp_tool
  • add_sub_agent
  • add_tech_stack
  • create_task
  • record_code_change
  • record_decision
  • record_guardian_intervention
  • record_status_transition
  • save_dependencies
Show 8 more tools
  • save_story_decomposition
  • save_task_analysis
  • sync_claude_code_agents
  • update_agent_prompt_templates
  • update_mcp_tool
  • update_sub_agent
  • update_task
  • update_tech_stack

Delete 5 · Delete, drop, revoke or wipe things.

  • delete_task
  • delete_user_story
  • remove_tech_stack
  • rollback_task
  • safe_delete_tasks_by_status

Not yet classified 4 · We could not tell from the name and description.

  • initialize_project_configuration
  • intelligent_decompose_story
  • prepare_task_for_execution
  • render_template

Files it touches

  • Any path the agent passes to its tools

Tools (62)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • add_code_pattern

    Add a reusable code pattern to the project library

  • add_feedback

    Add feedback/learning from task execution to improve future recommendations

  • add_guideline

    Add a project guideline or coding standard

  • add_mcp_tool

    Add an MCP tool configuration to the project

  • add_sub_agent

    Add a sub-agent (guardian) to the project configuration

  • add_tech_stack

    Add a technology stack entry to the project configuration

  • check_pattern_risk

    Check if a specific pattern has a history of failures and get risk assessment before using it. Provides immediate feedback on pattern safety.

  • create_task

    Creates a new task with title, description, status (backlog|todo|in_progress|done), dependencies, assignee, priority, and tags. ⚠️ IMPORTANT: The tool response includes automatic workflow guidance (nextSteps field) for analyzing the task before implementation. Always follow the nextSteps instructions to ensure complete metadata and dependency mapping.

  • delete_task

    Deletes a task. Checks for dependent tasks and prevents deletion if other tasks depend on it. Invalidates caches automatically.

  • delete_user_story

    Delete a user story and all its sub-tasks. Checks for completed work and external dependencies. Use force=true to delete user stories with completed sub-tasks.

  • detect_failure_patterns

    Automatically detect patterns with high failure rates to identify risky approaches. Returns patterns sorted by failure rate with risk assessments and recommendations.

  • get_code_changes

    Get all code changes for a task

  • get_decisions

    Get all decisions made for a task

  • get_execution_order

    Calculates the topological execution order for tasks based on dependencies. Uses Kahn's algorithm to detect circular dependencies and return tasks sorted by execution sequence. Handles edge cases: cycles (returns error with cycle path), multiple dependency chains (ensures all paths considered), and isolated tasks (included at end).

  • get_execution_prompt

    Generates an enriched execution prompt with full context for implementing a task. Call this after save_task_analysis to get a comprehensive prompt with dependencies, risks, patterns, and guidelines. ⚠️ IMPORTANT: The response includes nextSteps for implementation - follow the prompt and update task status to in_progress when you start.

Show 47 more tools
  • get_guardian_interventions

    Get all guardian interventions for a task

  • get_iteration_count

    Get the number of iterations (updates) for a task

  • get_pattern_stats

    Get detailed statistics for a specific pattern including frequency, success rate, and usage timeline

  • get_project_configuration

    Get the complete configuration for a project including tech stack, sub-agents, MCP tools, guidelines, and code patterns

  • get_project_info

    Returns information about the current project including name, status, and description

  • get_relevant_knowledge

    Gets relevant templates, patterns, and learnings for a task

  • get_resource_usage

    Get all tasks that touch a specific resource

  • get_similar_learnings

    Find similar learnings/feedback based on context and pattern matching

  • get_status_history

    Get status transition history for a task

  • get_task_conflicts

    Get potential conflicts for a task based on resource usage

  • get_task_context

    Gets comprehensive context for a task including dependencies, previous work, guidelines, and tech stack

  • get_task_dependency_graph

    Get the dependency graph (nodes and edges) for a specific task

  • get_task_history

    Get complete event history for a task including all status changes, decisions, code changes, and guardian interventions

  • get_task_snapshot

    Get a snapshot of a task at a specific point in time

  • get_task_stats

    Get aggregated statistics for a task including event counts and timeline

  • get_tasks_by_user_story

    Get all tasks belonging to a specific user story

  • get_top_patterns

    Get the most frequently used patterns across all tasks, sorted by frequency and recency

  • get_trending_patterns

    Get patterns that are trending (most used in recent days), useful for identifying current development patterns

  • get_user_stories

    Get all user stories with task counts for dashboard display

  • get_user_story_health

    Get health monitoring data for all user stories, showing current vs. suggested status, completion percentage, and safety flags for deletion

  • initialize_project_configuration

    Initialize default configuration for a project including tools and guardian agents

  • intelligent_decompose_story

    🚀 INTELLIGENT WORKFLOW: Generates a structured prompt for Claude Code to analyze the codebase and decompose a user story based on REAL project context. Claude Code will use Grep/Glob/Read to explore the codebase before creating tasks. Returns a prompt with instructions for Claude Code to follow.

  • list_learnings

    Lists learnings from past experiences

  • list_patterns

    Lists coding patterns learned from the codebase

  • list_tasks

    Lists all tasks, optionally filtered by status and/or category

  • list_templates

    Lists available prompt and code templates

  • prepare_task_for_execution

    Prepares a task for execution by generating a structured analysis request. Returns a prompt that guides Claude Code to analyze the codebase using its tools (Read, Grep, Glob). ⚠️ IMPORTANT: The response includes workflowInstructions field - follow it to know exactly what to do next. After analysis, call save_task_analysis with the results.

  • read_claude_code_agents

    Read and parse Claude Code agents from .claude/agents/ directory

  • record_code_change

    Record a code change made during task execution

  • record_decision

    Record a decision made during task execution

  • record_guardian_intervention

    Record a guardian intervention during task execution

  • record_status_transition

    Record a status transition for a task

  • remove_tech_stack

    Remove a tech stack entry from the project

  • render_template

    Renders a template with provided variables

  • rollback_task

    Rollback a task to a previous state at a specific timestamp

  • safe_delete_tasks_by_status

    Safely delete tasks by status, automatically preserving user stories with completed work and tasks with dependencies. Returns detailed report of what was deleted vs. preserved.

  • save_dependencies

    Save analyzed dependencies and detect potential conflicts with other tasks

  • save_story_decomposition

    Saves the decomposition analysis performed by Claude Code after exploring the codebase. Call this after intelligent_decompose_story once you've analyzed the codebase and created the task breakdown with real file paths and dependencies.

  • save_task_analysis

    Saves the codebase analysis performed by Claude Code. Call this after analyzing the codebase following the prepare_task_for_execution prompt. Records dependencies, risks, and recommendations. ⚠️ IMPORTANT: The response includes nextSteps guidance - follow it to get the enriched execution prompt with all context.

  • suggest_agents_for_task

    Get AI-powered agent suggestions for a task based on description and category. Returns top 3 most relevant agents with confidence scores

  • suggest_tools_for_task

    Get AI-powered MCP tool suggestions for a task based on description and category. Returns top 3 most relevant tools with confidence scores

  • sync_claude_code_agents

    Synchronize Claude Code agents to Orchestro database. Reads agents from .claude/agents/, parses YAML frontmatter and prompts, then upserts to sub_agents table

  • update_agent_prompt_templates

    Update prompt templates for all agent types with predefined best-practice templates

  • update_mcp_tool

    Update an existing MCP tool configuration

  • update_sub_agent

    Update an existing sub-agent configuration

  • update_task

    Updates an existing task. Validates status transitions and dependencies

  • update_tech_stack

    Update an existing tech stack entry

Signals

Weekly downloads
27
Last release
Oct 10, 2025 (1 year ago)
Last package publish
Oct 10, 2025 (1 year ago)

From the package registry.

Details

Registry name
io.github.khaoss85/orchestro
Version
2.1.0
Auth
No auth
Packages
npm @khaoss85/orchestro
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registry

More from khaoss85

Cite this page

Orchestro MCP server. Agent Mart. https://agentmart.dev/connectors/khaoss85-orchestro (last updated 2026-10-24)