Atlas / MCP servers / echoingvesper / Task Orchestrator

Task OrchestratorBLOCK

Name: Task Orchestrator
Author: echoingvesper

mcp/echoingvesper/task-orchestrator

MCP server by echoingvesper · ai agents · ai automation · ai framework · Audited 2026-10-08

⚑ Report / re-scan Source ↗

A Model Context Protocol server that provides task orchestration capabilities for AI assistants

Verdict

BLOCK

Grade

Trust score

42 /100

Exposed tools

50 34r · 12w · 4d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://github.com/EchoingVesper/mcp-task-orchestrator/releases/tag/v2.0.0)

A Model Context Protocol server that transforms how you work with AI by automatically documenting every decision, implementation, and test as you build. Think of it as the memory layer for AI-assisted development that ensures no context is ever lost.

Overview

The MCP Task Orchestrator provides intelligent task orchestration, specialized AI roles, and persistent memory for AI-assisted development. Built with Clean Architecture principles, it automatically detects project structure and saves artifacts appropriately.

Document Type: Project Overview & User Guide Target Audience: Developers using MCP clients (Claude Desktop, Cursor, VS Code, etc.) Prerequisites: Python 3.8+, MCP-compatible client Last Updated: 2025-01-13

Key Features

Documentation Automation: Every task generates comprehensive, searchable artifacts
Specialist AI Roles: Architect, Implementer, Tester, Reviewer, Documenter, and more
Persistent Memory: Never lose context - all decisions and implementations are preserved
Workspace Awareness: Automatically detects project structure and saves artifacts appropriately
Template System: 13 tools for creating reusable task templates
Clean Architecture: Built with modern software design principles
Universal MCP Compatibility: Works across Claude Desktop, Cursor, Windsurf, VS Code + extensions

Quick Start

Prerequisites

Python 3.8+
One or more MCP clients (Claude Desktop, Cursor IDE, Windsurf, or VS Code with extensions)

Installation

Install: pip install mcp-task-orchestrator
*Configure

Read from source at commit 960d933fc218OBSERVED · 2026-10-08

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add mcp-task-orchestrator --env MCP_TASK_ORCHESTRATOR_DEV_API_KEY=${MCP_TASK_ORCHESTRATOR_DEV_API_KEY} --env PYPI_API_TOKEN=${PYPI_API_TOKEN} --env PYPI_TEST_TOKEN=${PYPI_TEST_TOKEN} -- uvx mcp-task-orchestrator

claude-desktop

{
  "mcpServers": {
    "mcp-task-orchestrator": {
      "command": "uvx",
      "args": [
        "mcp-task-orchestrator"
      ],
      "env": {
        "MCP_TASK_ORCHESTRATOR_DEV_API_KEY": "${MCP_TASK_ORCHESTRATOR_DEV_API_KEY}",
        "PYPI_API_TOKEN": "${PYPI_API_TOKEN}",
        "PYPI_TEST_TOKEN": "${PYPI_TEST_TOKEN}"
      }
    }
  }
}

Exposed tools (50)

34 read · 12 write · 4 destructive. Blast radius: 4 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`auto_append_create_rule`	write	Create a new auto-append rule for automatic task creation
`auto_append_delete_rule`	destructive	Delete an auto-append rule
`auto_append_get_rule`	read	Get detailed information about a specific auto-append rule
`auto_append_get_statistics`	read	Get auto-append engine statistics and monitoring data
`auto_append_list_rules`	read	List auto-append rules with optional filtering
`auto_append_test_condition`	read	Test a condition against sample event and task data
`echo`	read	Echo back the input
`initialize_session`	read	Initialize a new task orchestration session
`orchestrator_cancel_task`	read	Cancel an in-progress generic task gracefully
`orchestrator_cleanup_partial_artifacts`	read	Clean up old partial artifacts
`orchestrator_cleanup_sessions`	read	Clean up old, completed, or orphaned sessions
`orchestrator_complete_subtask`	read	Mark a subtask as completed with results
`orchestrator_complete_subtask_enhanced`	read	Enhanced subtask completion with streaming artifacts and partial response detection
`orchestrator_complete_task`	read	Mark a task as complete and store detailed work as artifacts to prevent context limit issues
`orchestrator_continue_partial_artifact`	read	Continue writing to a partial artifact
`orchestrator_create_generic_task`	write	Create a new generic task with rich metadata and flexible structure
`orchestrator_database_health`	read	Check database migration system health and status
`orchestrator_delete_task`	destructive	Safely delete a generic task and handle its dependencies
`orchestrator_execute_subtask`	write	Execute a specific subtask with specialist context
`orchestrator_execute_task`	write	Get specialist context and prompts for executing a specific task
`orchestrator_get_status`	read	Get current status of tasks and progress
`orchestrator_health_check`	read	Check server health and readiness for operations
`orchestrator_initialize_session`	read	Initialize a new task orchestration session
`orchestrator_list_partial_artifacts`	read	List all partial artifacts that can be resumed
`orchestrator_list_sessions`	read	List all orchestration sessions with status and metadata
`orchestrator_maintenance_coordinator`	read	Automated maintenance task coordination for task cleanup, validation, and handover preparation
`orchestrator_migration_status`	read	Get database migration status and history
`orchestrator_plan_task`	write	Create a new task using Clean Architecture
`orchestrator_query_tasks`	read	Query and filter generic tasks with advanced search capabilities
`orchestrator_reconnect_test`	read	Test client reconnection capability and connection status
`orchestrator_restart_server`	write	Trigger a graceful server restart with state preservation
`orchestrator_restart_status`	write	Get current status of restart operation
`orchestrator_resume_partial_artifact`	read	Resume work on a partial artifact that was interrupted
`orchestrator_resume_session`	read	Resume a previous orchestration session by ID
`orchestrator_session_status`	read	Get detailed status of a specific session
`orchestrator_shutdown_prepare`	read	Check server readiness for graceful shutdown
`orchestrator_synthesize_results`	read	Combine completed subtasks into final result
`orchestrator_update_task`	write	Update an existing generic task
`template_create`	write	Create a new JSON5 template in the template system
`template_delete`	destructive	Delete a template from storage
`template_get_installation_status`	read	Get status of template installations and coverage
`template_info`	read	Get detailed information about a template
`template_install_default_library`	write	Install the default template library
`template_install_examples`	write	Install example templates to get started with the template system
`template_instantiate`	write	Create tasks from a template with parameter substitution
`template_list`	read	List available templates with optional filtering
`template_load`	read	Load a template and show its content and structure
`template_uninstall`	destructive	Uninstall a template
`template_validate`	read	Validate template syntax, structure, and security
`template_validate_all`	read	Validate all installed templates for security and syntax

Trust audit

BLOCKgrade F · trust 42/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (16 observation(s))
Network: declared (10 observation(s))
Shell: declared (11 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (25)

CRITICALHard-coded secrets · secret.slack · CWE-798, CWE-321

.claude/commands/git-operations/secrets-scanner-fix.md:53

| Slack bot tokens (`xoxb-*` format) | `FAKE-XOXB-REDACTED-FOR-TESTING` |

CRITICALHard-coded secrets · secret.slack · CWE-798, CWE-321

.claude/commands/git-operations/secrets-scanner-fix.md:128

sed -i "s/[ORIGINAL_XOXB_PATTERN]/FAKE-XOXB-REDACTED-FOR-TESTING/g" tests/security/test_information_disclosure.py

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

scripts/testing/execute_test_direct.py:10

exec(open('standalone_migration_test.py').read())

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table