JJ Planner MCP Server
Enables AI agents to manage projects, tasks, and schedules in JJ Planner through CRUD operations.
README
JJ Planner MCP Server
An MCP (Model Context Protocol) server that connects AI agents (Cursor, Claude, etc.) to JJ Planner — a project management PWA. Agents can query, create, update, and delete projects, tasks, and schedules through this server.
Requirements
- Node.js 22.x or higher
- A valid JJ Planner API key (issued from JJ Planner settings page)
Installation
Via npm (recommended):
npm install -g @vncy/jj-planner-mcp
From source:
git clone https://github.com/Vince-Yi/-vncy-jj-planner-mcp.git
cd -vncy-jj-planner-mcp
npm install
npm run build
Configuration
Copy .env.example to .env and fill in your credentials:
cp .env.example .env
JJ_PLANNER_API_BASE_URL=https://your-backend-url.com
JJ_PLANNER_API_KEY=jjp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
| Variable | Description |
|---|---|
JJ_PLANNER_API_BASE_URL |
Base URL of the JJ Planner backend |
JJ_PLANNER_API_KEY |
API key in the format jjp_ + 64-char hex (68 chars total) |
Registering with Cursor
Add the following to your Cursor mcp.json:
{
"mcpServers": {
"jj-planner": {
"command": "npx",
"args": ["-y", "@vncy/jj-planner-mcp"],
"env": {
"JJ_PLANNER_API_BASE_URL": "https://your-backend-url.com",
"JJ_PLANNER_API_KEY": "jjp_..."
}
}
}
}
Registering with Claude Code
Add to your claude_desktop_config.json (or Claude Code MCP settings):
{
"mcpServers": {
"jj-planner": {
"command": "npx",
"args": ["-y", "@vncy/jj-planner-mcp"],
"env": {
"JJ_PLANNER_API_BASE_URL": "https://your-backend-url.com",
"JJ_PLANNER_API_KEY": "jjp_..."
}
}
}
}
Available Tools
Projects
| Tool | Required Args | Optional Args | Description |
|---|---|---|---|
list_projects |
— | — | List all projects |
get_project |
projectId |
— | Get project details |
Groups
| Tool | Required Args | Optional Args | Description |
|---|---|---|---|
list_groups |
projectId |
— | List groups in a project |
Tasks
| Tool | Required Args | Optional Args | Description |
|---|---|---|---|
list_tasks |
projectId |
— | List tasks in a project |
get_task |
taskId |
— | Get task details |
create_task |
projectId, title |
groupId, assignees, status, progress |
Create a new task |
update_task |
taskId |
title, groupId, assignees, status, progress |
Update a task |
delete_task |
taskId |
— | Delete a task |
Task status values: pending / in_progress / completed
Task progress: integer from 0 to 100
Schedules
| Tool | Required Args | Optional Args | Description |
|---|---|---|---|
list_schedules |
projectId |
taskId |
List schedules (all or per task) |
create_schedule |
taskId, projectId, startDate, startHalf, endDate, endHalf |
title |
Create a new schedule |
update_schedule |
scheduleId |
startDate, startHalf, endDate, endHalf, title |
Update a schedule |
delete_schedule |
scheduleId |
— | Delete a schedule |
Date format: YYYY-MM-DD
Half-day values: AM / PM
Project Structure
jj-planner-mcp/
├── package.json
├── tsconfig.json
├── .env.example
└── src/
├── index.ts # MCP server entry point, tool registration, stdio transport
├── client.ts # axios instance with X-API-Key header and response unwrapping
└── tools/
├── projects.ts # list_projects, get_project
├── groups.ts # list_groups
├── tasks.ts # list_tasks, get_task, create_task, update_task, delete_task
└── schedules.ts # list_schedules, create_schedule, update_schedule, delete_schedule
Scripts
| Command | Description |
|---|---|
npm run build |
Compile TypeScript to dist/ |
npm start |
Run the compiled server |
npm run dev |
Run directly with ts-node (development) |
Authentication
Every request to the JJ Planner backend includes the following header:
X-API-Key: <your-api-key>
The API key can be generated from the JJ Planner settings page. It follows the format jjp_ followed by 64 hexadecimal characters (68 characters total).
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。