PlanManager MCP Server
Uses SQLite as the data persistence layer for storing and managing hierarchical plans, including CRUD operations, status tracking, and search functionality.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@PlanManager MCP Server create a travel plan for Japan trip next month"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PlanManager MCP Server
🚀 基于FastMCP框架和SQLite的通用计划管理系统
一个功能强大的MCP服务器,支持创建、管理和追踪各类计划,特别适合旅行计划、学习计划、工作任务等多层级项目管理。
✨ 特性
📋 核心功能
🏗️ 层级管理 - 支持父子计划的层级结构
🗄️ 数据持久化 - 基于SQLite的可靠数据存储
🔍 智能搜索 - 按名称和描述搜索计划
📊 统计分析 - 实时查看计划完成情况
🔄 状态管理 - 完整的计划生命周期管理
🎯 快速模板
✈️ 旅行计划模板 - 一键创建完整的旅行计划
📚 学习计划模板 - 自动生成学习进度安排
💼 工作计划模板 - 灵活的任务分解
🛠️ 高级功能
📝 批量创建 - 支持一次性创建多个子计划
🏷️ 分类管理 - 多种类别标签支持
📅 时间管理 - 灵活的开始时间和截止日期
💾 元数据扩展 - JSON格式的自定义数据支持
Related MCP server: Follow Plan MCP Server
🚀 快速开始
环境要求
Python 3.14+
UV (推荐) 或 pip
安装
# 克隆项目
git clone <your-repo-url>
cd plan-server-mcp
# 安装依赖
uv sync
# 或者使用pip
pip install -e .运行
# 启动MCP服务器
uv run main.py
# 或者
python main.py📖 使用指南
基础操作
创建计划
# 创建通用计划
create_plan(
name="我的新项目",
description="这是一个重要的项目",
category="工作",
scheduled_at="2025-01-01",
deadline="2025-03-31"
)添加子计划
# 添加子步骤
add_step(
plan_id=1,
name="需求分析",
description="完成项目需求文档",
scheduled_at="2025-01-05"
)快速模板
🌍 创建旅行计划
create_travel_plan(
destination="日本",
start_date="2025-04-01",
end_date="2025-04-10",
budget=15000,
description="东京、大阪、京都文化之旅"
)📖 创建学习计划
create_study_plan(
subject="机器学习",
duration_weeks=8,
start_date="2025-01-15",
description="深入学习机器学习算法和实践"
)查询和管理
查看计划
# 列出所有计划
list_plans()
# 按类别筛选
list_plans(category="旅行")
# 查看详情
get_plan_details(plan_id=1)更新状态
# 更新计划状态
update_plan_status(plan_id=1, status="in_progress")搜索和统计
# 搜索计划
search_plans(keyword="学习")
# 获取统计信息
get_plan_statistics()📊 数据库设计
表结构
CREATE TABLE plans (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT NOT NULL, -- 计划名称
description TEXT, -- 描述
category TEXT DEFAULT 'general', -- 类别
parent_id INTEGER, -- 父计划ID
scheduled_at DATE, -- 开始时间
deadline DATE, -- 截止时间
status TEXT DEFAULT 'pending', -- 状态
metadata TEXT, -- 元数据(JSON)
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
FOREIGN KEY (parent_id) REFERENCES plans (id) ON DELETE CASCADE
);状态说明
pending- 待开始in_progress- 进行中completed- 已完成cancelled- 已取消
类别标签
general- 通用旅行- 旅行相关学习- 学习计划工作- 工作任务健康- 健康管理习惯- 习惯培养
🏗️ 架构设计
PlanManager MCP Server
├── FastMCP Framework # MCP协议层
├── SQLiteDB # 数据持久化层
├── Plan Management # 业务逻辑层
└── Template System # 模板系统核心组件
1. SQLiteDB 类
数据库连接管理
CRUD操作封装
事务支持
2. MCP Tools
create_plan- 创建计划add_step- 添加子步骤update_plan_status- 更新状态get_plan_details- 获取详情list_plans- 列出计划delete_plan- 删除计划
3. 模板系统
create_travel_plan- 旅行计划模板create_study_plan- 学习计划模板create_plan_batch- 批量创建
🔧 开发
项目结构
plan-server-mcp/
├── main.py # 主程序文件
├── pyproject.toml # 项目配置
├── uv.lock # 依赖锁定文件
├── README.md # 项目文档
└── USAGE.md # 使用指南本地开发
# 开发模式运行
python main.py
# 代码检查
python -m py_compile main.py
# 测试数据库
sqlite3 plans.db ".schema"📝 API 参考
核心工具
工具名 | 功能描述 | 参数 |
| 创建计划 | name, description, category, scheduled_at, deadline, metadata |
| 添加子步骤 | plan_id, name, description, scheduled_at, metadata |
| 更新状态 | plan_id, status |
| 获取详情 | plan_id |
| 列出计划 | category, status |
| 删除计划 | plan_id |
模板工具
工具名 | 功能描述 | 参数 |
| 创建旅行计划 | destination, start_date, end_date, budget, description |
| 创建学习计划 | subject, duration_weeks, start_date, description |
| 批量创建 | name, children, category, description |
实用工具
工具名 | 功能描述 | 参数 |
| 搜索计划 | keyword |
| 获取统计 | 无 |
| 重新安排时间 | plan_id, new_time |
🤝 贡献
欢迎提交 Issue 和 Pull Request!
开发流程
Fork 项目
创建特性分支
提交更改
创建 Pull Request
📄 许可证
本项目采用 MIT 许可证 - 查看 LICENSE 文件了解详情。
🙏 致谢
📞 支持
如有问题或建议,请:
Made with ❤️ using FastMCP
Available Tools
20 toolsadd_stepC
Add a step (sub-task) to an existing plan.
Args: plan_id:父计划的id。 name:步骤的名称。 description:有关此步骤的详细信息。 scheduled_at:何时应该完成此步骤(ISO 8601)。 元数据:用于额外数据的JSON字符串。
Inputs: plan_id (required), name (required), description, scheduled_at, +1 more. Returns: result
backup_plansB
备份所有计划数据
Inputs: no named parameters. Returns: result
cancel_travel_planB
取消旅行计划 - 当用户时间变动时批量删除所有旅行相关计划
Args: reason: 取消原因(默认为"时间变动") keyword: 搜索关键词(默认搜索"旅行"相关的计划)
Inputs: reason, keyword. Returns: result
create_planB
创建一个通用计划.
Args:
name: 计划的名称(例如,“我要去云南旅行”、“学习计划一周的Python课程安排”).
description: 计划的详细描述.
category: 类别(例如,“旅行”、“学习”、“习惯”、“工作”).
scheduled_at: 计划开始时(ISO 8601格式:YYYY-MM-DD).
deadline: 计划应何时完成(ISO 8601格式:YYYY-MM-DD).
metadata: 包含额外数据的JSON字符串(例如,“{“budget”:500}”).
Inputs: name (required), description, category, scheduled_at, +2 more. Returns: result
create_plan_batchA
Create a plan with multiple steps in one go. Useful for generating full schedules like "Weekly Study Plan" or "21-Day Challenge".
Args: name: Name of the main plan. children: A JSON string representing a LIST of step objects. Example: '[{"name": "Day 1", "scheduled_at": "2025-12-25"}, {"name": "Day 2"}]' category: Category for the plan and all children.
Inputs: name (required), children (required), category, description. Returns: result
create_study_planB
快速创建学习计划模板.
Args: subject: 学习主题(例如,"Python编程"、"英语口语"、"数据分析") duration_weeks: 学习周期(周数) start_date: 开始日期 (YYYY-MM-DD) description: 学习计划描述
Inputs: subject (required), duration_weeks (required), start_date (required), description. Returns: result
create_travel_planC
快速创建旅行计划模板.
Args: destination: 目的地(例如,"云南"、"日本"、"欧洲") start_date: 开始日期 (YYYY-MM-DD) end_date: 结束日期 (YYYY-MM-DD) budget: 预算金额 description: 旅行描述
Inputs: destination (required), start_date (required), end_date (required), budget, +1 more. Returns: result
delete_planC
删除计划(级联删除所有子计划)
Inputs: plan_id (required). Returns: result
delete_plan_by_nameB
按名称删除计划(级联删除所有子计划)- 适合语音交互
Args: plan_name: 要删除的计划名称(支持模糊匹配)
Inputs: plan_name (required). Returns: result
fix_old_datesB
修复过去的日期 - 将指定年份之前的计划日期更新为指定年份
Args: year: 目标年份(默认为"2025")
Inputs: year. Returns: result
get_operation_logsC
获取操作日志记录
Args: limit: 显示最近的日志条数(默认20条)
Inputs: limit. Returns: result
get_plan_detailsB
Get the full details and structure of a plan, including all its steps.
Inputs: plan_id (required). Returns: result
get_plan_statisticsC
获取计划统计信息.
Inputs: no named parameters. Returns: result
guided_plan_creationC
引导式创建计划 - 一步步帮助用户创建完整计划
Args: plan_type: 计划类型 ("general", "travel", "study", "work", "health")
Inputs: plan_type. Returns: result
list_plansB
List top-level plans (items without a parent).
Args: category: Filter by category (e.g., "travel", "study"). status: Filter by status (e.g., "pending", "completed").
Inputs: category, status. Returns: result
preview_delete_planA
预览删除计划的影响(不实际删除)
Args: plan_id: 要预览的计划ID
Inputs: plan_id (required). Returns: result
reschedule_planB
Change the scheduled time for a plan or step.
Args: plan_id: The ID of the item. new_time: New ISO 8601 date string (e.g., "2025-12-25").
Inputs: plan_id (required), new_time (required). Returns: result
search_plansC
搜索计划(按名称或描述).
Args: keyword: 搜索关键词
Inputs: keyword (required). Returns: result
update_plan_statusC
Update the status of a plan or step.
Args: plan_id: The ID of the item. status: New status ('pending', 'in_progress', 'completed', 'cancelled').
Inputs: plan_id (required), status (required). Returns: result
validate_and_save_planC
验证计划数据并保存到数据库
Args: name: 计划名称 plan_data: 计划数据的JSON字符串 auto_save: 是否自动保存到数据库
Inputs: name (required), plan_data (required), auto_save. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 20 tools
There is significant overlap between tools like create_plan, create_plan_batch, create_study_plan, create_travel_plan, and guided_plan_creation, which all create plans with varying approaches. However, descriptions help clarify distinctions (e.g., batch creation vs. guided creation), and tools like backup_plans or fix_old_dates have unique purposes, preventing complete confusion.
Most tools follow a consistent verb_noun pattern (e.g., create_plan, delete_plan, update_plan_status), with clear actions and targets. Minor deviations exist, such as backup_plans (noun_verb) and get_operation_logs (get_noun_noun), but the overall naming is predictable and readable.
With 20 tools, the count feels heavy for a plan management server, bordering on excessive. While the domain supports many operations, some tools (e.g., create_plan_batch vs. guided_plan_creation) could be consolidated, making the set feel slightly bloated rather than well-scoped.
The tool set provides comprehensive coverage for plan management, including CRUD operations (create, get, update, delete), specialized templates (study, travel), batch and guided creation, status updates, rescheduling, search, statistics, logs, backups, and validation. No obvious gaps exist for core workflows in this domain.
Maintenance
Related MCP Connectors
Minimal issue tracker: projects, objectives and trackable plans, written by agents over MCP.
A project planning board your AI reads and updates over MCP, so the plan stays one plan.
AI workflow/MCP implementation package planner.
Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables AI agents to create, manage, and search hierarchical plans with phases, tasks, and milestones through a comprehensive planning API. Supports CRUD operations, batch updates, rich context retrieval, and artifact management for structured project planning.3737 npm4MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for intelligent project planning and task management featuring task tracking, bug reporting, and feature specification with SQLite persistence. It includes full-text search capabilities and automatic filesystem synchronization to keep project data organized and accessible.MIT
- AlicenseNot gradedqualityDmaintenanceAn intelligent task management server that generates context-aware engineering plans using LLM-powered workflows and interactive requirement elicitation. It features persistent SQLite storage, category-based planning strategies, and automated progress tracking for software development projects.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI orchestrators to manage hierarchical implementation roadmaps with phases, tasks, and plan-change tracking.Apache 2.0