TimeCard MCP
An MCP server that automates TimeCard timesheet management using Playwright browser automation. It enables users to manage projects, activities, and daily hours entries through natural language interactions.
README
TimeCard MCP
A Model Context Protocol (MCP) server for automating TimeCard timesheet management using Playwright browser automation.
🚀 Quick Start
Recommended: Use npx to run the TimeCard MCP server. This approach automatically fetches the latest version without manual maintenance (requires Node.js v18+).
# 1. Set environment variables (replace with your actual credentials)
export TIMECARD_USERNAME="your_username"
export TIMECARD_PASSWORD="your_password"
export TIMECARD_BASE_URL="http://your-timecard-server/app/"
# 2. Run the server
npx git+https://github.com/keith-hung/timecard-mcp.git
Claude Desktop Integration
You can use the npx method directly in Claude Desktop configuration:
{
"mcpServers": {
"timecard": {
"command": "npx",
"args": ["git+https://github.com/keith-hung/timecard-mcp.git"],
"env": {
"TIMECARD_USERNAME": "your_username",
"TIMECARD_PASSWORD": "your_password",
"TIMECARD_BASE_URL": "http://your-timecard-server/app/"
}
}
}
}
Benefits:
- Automatically stays up-to-date
- No manual installation or build required
- Simple configuration
- npx caches downloaded packages - won't re-download every time
Note: Ensure your TIMECARD_BASE_URL includes the application path (e.g., http://your-timecard-server/app/).
🛠️ Advanced Setup: Local Development
For developers or users requiring specific version control, offline usage, or code modifications, you can opt for local installation:
1. Local Setup
# 1. Clone the repository
git clone https://github.com/keith-hung/timecard-mcp.git
cd timecard-mcp
# 2. Install dependencies and build
npm install
npm run build
2. Environment Configuration
The server requires the following environment variables to connect to your TimeCard system. You can create a .env file in the project root or set them in your shell:
export TIMECARD_USERNAME="your_username"
export TIMECARD_PASSWORD="your_password"
export TIMECARD_BASE_URL="http://your-timecard-server/app/"
3. Add to Claude Desktop (Local Version)
Edit your ~/Library/Application Support/Claude/claude_desktop_config.json file:
{
"mcpServers": {
"timecard": {
"command": "node",
"args": ["/absolute/path/to/timecard-mcp/dist/index.js"],
"env": {
"TIMECARD_USERNAME": "your_username",
"TIMECARD_PASSWORD": "your_password",
"TIMECARD_BASE_URL": "http://your-timecard-server/app/"
}
}
}
}
Note: Replace /absolute/path/to/timecard-mcp/ with the actual path where you cloned this repository.
When to use local installation:
- Code modification or extension required
- Specific version control needs
- Fully offline environment
- Development and debugging requirements
4. Restart Claude Desktop
After configuration, restart Claude Desktop. You should now see TimeCard tools available!
📚 Documentation
- FEATURES.md - Detailed documentation of all available MCP tools, parameters, return values, and usage examples
- DEVELOPMENT.md - Developer guide for understanding, modifying, or extending TimeCard MCP
🔧 Available Tools
The TimeCard MCP server provides 13 tools organized into 4 categories:
Authentication
timecard_login- Login to TimeCard systemtimecard_logout- Logout from TimeCard systemtimecard_check_session- Check current session status
Data Retrieval
timecard_get_projects- Get available projectstimecard_get_activities- Get activities for a projecttimecard_get_timesheet- Get timesheet data for a week
Timesheet Operations
timecard_set_timesheet_entry- Set project and activity for an entrytimecard_set_daily_hours- Set hours for a specific daytimecard_set_daily_note- Set note for a specific daytimecard_clear_daily_hours- Clear all hours for a specific day
Management
timecard_save_timesheet- Save timesheet changes permanentlytimecard_validate_timesheet- Validate timesheet for errorstimecard_get_summary- Get timesheet summary statistics
See FEATURES.md for detailed usage.
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。