Task Orchestration
任务编排器 (Task Orchestrator)
一个用于任务编排和管理的模型上下文协议 (MCP) 服务器。此工具可帮助将目标分解为可管理的任务并跟踪其进度。
如何使用
理想情况下,LLM 应该能够理解何时使用此 MCP 工具。但作为一个示例提示词,类似这样的内容可能会起作用:
“为我创建一个新的开发目标。目标是‘实现用户身份验证’,它是针对‘my-web-app’存储库的。”
如果您遇到任何问题,请在顶部的“Discussions”选项卡中创建一个新议题,让我知道。
Related MCP server: Claudia
功能
创建和管理目标
将目标分解为层级任务
跟踪任务完成状态
支持子任务以及父任务与子任务之间的依赖管理
使用 LokiDB 进行持久化存储
路线图
复杂的任务/目标相互依赖编排
目标删除
完成处置
进度可视化 UI
API 参考
任务 ID 命名约定
任务 ID 使用点号表示法(例如,“1”、“1.1”、“1.1.1”),其中每个段代表层级中的一个级别。
对于每个新目标,顶级任务 ID 从“1”开始并按顺序递增(例如,“1”、“2”、“3”)。
子任务的 ID 是通过在其父级 ID 后附加一个新段形成的(例如,“1.1”是“1”的子任务)。
goalId和taskId的组合保证是唯一的。
工具
服务器提供以下工具(基于 build/index.js):
create_goal创建一个新目标
参数:
{ description: string; // The goal description repoName: string; // The repository name associated with this goal }示例输入:
{ "description": "Implement user authentication", "repoName": "example/auth-service" }返回:
{ goalId: number }
add_tasks向目标添加多个任务。任务可以以层级结构提供。对于作为现有任务子级的任务,请使用
parentId字段。该操作是事务性的:要么批处理中的所有任务都成功,要么整个操作失败。参数:
{ goalId: number; // ID of the goal to add tasks to (number) tasks: Array<{ title: string; // Title of the task (string) description: string; // Detailed description of the task (string) parentId?: string | null; // Optional parent task ID for tasks that are children of *existing* tasks. Do not use for new subtasks defined hierarchically within this batch. subtasks?: Array<any>; // An array of nested subtask objects to be created under this task. }>; }示例输入:
{ "goalId": 1, "tasks": [ { "title": "Design database schema", "description": "Define tables for users, roles, and permissions", "subtasks": [ { "title": "Create ERD", "description": "Draw entity-relationship diagram" } ] }, { "title": "Implement user registration", "description": "Create API endpoint for new user signup", "parentId": "1" } ] }返回:
HierarchicalTaskResponse[]。HierarchicalTaskResponse对象经过简化,不包含createdAt、updatedAt或parentId。
remove_tasks软删除目标中的多个任务。任务被标记为已删除但仍保留在系统中。默认情况下,除非明确删除其子级,否则无法软删除具有子任务的父任务。除非将
includeDeletedTasks设置为 true,否则软删除的任务默认从get_tasks结果中排除。参数:
{ goalId: number; // ID of the goal to remove tasks from taskIds: string[]; // IDs of the tasks to remove (array of strings). Task IDs use dot-notation (e.g., "1", "1.1"). deleteChildren?: boolean; // Whether to delete child tasks along with the parent (boolean). Defaults to false. If false, attempting to delete a parent task with existing subtasks will throw an error. }示例输入(不删除子级):
{ "goalId": 1, "taskIds": ["2", "3"] }示例输入(删除子级):
{ "goalId": 1, "taskIds": ["1"], "deleteChildren": true }返回:
{ removedTasks: TaskResponse[], completedParents: TaskResponse[] }。TaskResponse对象经过简化,不包含createdAt、updatedAt或parentId。
get_tasks获取目标的任务。任务 ID 使用点号表示法(例如,“1”、“1.1”、“1.1.1”)。当指定
includeSubtasks时,响应将返回层级任务对象。否则,将返回不包含createdAt、updatedAt或parentId的简化任务对象。参数:
{ goalId: number; // ID of the goal to get tasks for (number) taskIds?: string[]; // Optional: IDs of tasks to fetch (array of strings). If null or empty, all tasks for the goal will be fetched. includeSubtasks?: "none" | "first-level" | "recursive"; // Level of subtasks to include: "none" (only top-level tasks), "first-level" (top-level tasks and their direct children), or "recursive" (all nested subtasks). Defaults to "none". includeDeletedTasks?: boolean; // Whether to include soft-deleted tasks in the results (boolean). Defaults to false. }示例输入:
{ "goalId": 1, "includeSubtasks": "recursive", "includeDeletedTasks": true }返回:
TaskResponse[]。TaskResponse对象经过简化,不包含createdAt、updatedAt或parentId。
complete_task_status将任务标记为完成。默认情况下,如果父任务有未完成的子任务,则无法将其标记为完成。
参数:
{ goalId: number; // ID of the goal containing the tasks taskIds: string[]; // IDs of the tasks to update (array of strings). Task IDs use dot-notation (e.g., "1", "1.1"). completeChildren?: boolean; // Whether to complete all child tasks recursively (boolean). Defaults to false. If false, a task can only be completed if all its subtasks are already complete. }示例输入(不完成子级):
{ "goalId": 1, "taskIds": ["1", "2"] }示例输入(完成子级):
{ "goalId": 1, "taskIds": ["1"], "completeChildren": true }返回:
TaskResponse[]。TaskResponse对象经过简化,不包含createdAt、updatedAt或parentId。
使用示例
创建目标和任务
// Create a new goal. Its top-level tasks will start with ID "1".
const goal = await callTool('create_goal', {
description: 'Implement user authentication',
repoName: 'user/repo'
});
// Add a top-level task
const task1 = await callTool('add_tasks', {
goalId: goal.goalId,
tasks: [
{
title: 'Set up authentication middleware',
description: 'Implement JWT-based authentication'
}
]
});
// task1.addedTasks[0].id will be "1"
// Add a subtask to the previously created task "1"
const task2 = await callTool('add_tasks', {
goalId: goal.goalId,
tasks: [
{
title: 'Create login endpoint',
description: 'Implement POST /auth/login',
parentId: "1" // ParentId must refer to an *already existing* task ID
}
]
});
// task2.addedTasks[0].id will be "1.1"管理任务状态
// Mark a parent task as complete, which will also complete its children
await callTool('complete_task_status', {
goalId: 1,
taskIds: ["1"],
completeChildren: true
});
// Get all tasks including subtasks recursively
const allTasks = await callTool('get_tasks', {
goalId: 1,
includeSubtasks: "recursive"
});删除任务
// Attempt to remove a parent task without deleting children (will fail if it has subtasks)
try {
await callTool('remove_tasks', {
goalId: 1,
taskIds: ["1"]
});
} catch (error) {
console.error(error.message); // Expected to throw an error if subtasks exist
}
// Remove a parent task and its children
await callTool('remove_tasks', {
goalId: 1,
taskIds: ["1"],
deleteChildren: true
});开发
先决条件
Node.js 18+
pnpm
设置
安装依赖:
pnpm install构建项目:
pnpm build运行测试:
pnpm test
项目结构
src/- 源代码index.ts- 主服务器实现storage.ts- 数据持久层types.ts- TypeScript 类型定义prompts.ts- AI 提示词模板__tests__/- 测试文件
许可证
MIT
Available Tools
5 toolsadd_tasksA
Add multiple tasks to a goal. Tasks can be provided in a hierarchical structure. For tasks that are children of existing tasks, use the parentId field. The operation is transactional: either all tasks in the batch succeed, or the entire operation fails.
Inputs: goalId (required), tasks (required).
complete_task_statusC
Update the completion status of tasks. Task IDs use a dot-notation (e.g., "1", "1.1", "1.1.1"). Responses will return simplified task objects without createdAt, updatedAt, or parentId.
Inputs: goalId (required), taskIds (required), completeChildren.
create_goalC
Create a new goal
Inputs: description (required), repoName.
get_tasksB
Get tasks for a goal. Task IDs use a dot-notation (e.g., "1", "1.1", "1.1.1"). When includeSubtasks is specified, responses will return hierarchical task objects. Otherwise, simplified task objects without createdAt, updatedAt, or parentId will be returned.
Inputs: goalId (required), taskIds, includeSubtasks, includeDeletedTasks.
remove_tasksA
Soft-delete multiple tasks from a goal. Tasks are marked as deleted but remain in the system. Task IDs use a dot-notation (e.g., "1", "1.1", "1.1.1"). Responses will return simplified task objects without createdAt, updatedAt, or parentId. Soft-deleted tasks are excluded by default from get_tasks results unless includeDeletedTasks is set to true.
Inputs: goalId (required), taskIds (required), deleteChildren.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: add_tasks for batch creation, complete_task_status for updating status, create_goal for goal creation, get_tasks for retrieval, and remove_tasks for soft deletion. There is no overlap in functionality, making it easy for an agent to select the correct tool.
All tools follow a consistent verb_noun pattern (e.g., add_tasks, complete_task_status, create_goal, get_tasks, remove_tasks). The naming is uniform and predictable, with no deviations in style or convention.
With 5 tools, the server is well-scoped for task orchestration, covering core operations like creation, retrieval, update, and deletion. Each tool serves a necessary function without redundancy, fitting typical server sizes of 3-15 tools.
The tool set provides strong coverage for task management, including CRUD-like operations (create, get, update status, soft delete) and goal creation. A minor gap exists in updating goal details or hard-deleting tasks, but agents can work around this with the available tools.
Maintenance
Related MCP Connectors
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
LLM Orchestration Agent (Mcp)
Task manager for AI agents. Orchestrate agents to achieve large goals in unified control plane.
Headless task management for bots, apps and AI agents. Remote MCP server, OAuth or access token.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceAn MCP server that automates project task breakdown, dependency management, and smart task recommendations, integrating with LLMs like Gemini and OpenAI.7-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to manage hierarchical tasks, track progress, handle dependencies, and coordinate work through an MCP server.49 npm15GPL 3.0
- AlicenseNot gradedqualityDmaintenanceA comprehensive MCP server that enables LLMs to manage Google Tasks and task lists through workflow-oriented tools for creation, updating, searching, and organizing tasks.MIT
- FlicenseAqualityDmaintenanceA production-ready MCP server for task management, enabling LLMs to create, list, and manage tasks via tools and resources, with support for local stdio and cloud Streamable HTTP deployment.5-