Timesheet MCP Server
A Model Context Protocol (MCP) server for timesheet management system, built with FastMCP 2.0.
🚀 Quick Start
Installation
Using uvx (recommended):
uvx timesheet-mcp-server
Using pip:
pip install timesheet-mcp-server
Configuration
Set up your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"timesheet": {
"command": "uvx",
"args": ["timesheet-mcp-server"],
"env": {
"TIMESHEET_API_BASE_URL": "http://127.0.0.1:8080/api",
"TIMESHEET_API_TOKEN": "your-jwt-token"
}
}
}
}
✨ Features
Time Entry Queries (2)
- Get my time entries with filters
- Get recent time entries
User Queries (3)
- Search users by name
- Get user details
- Get user time entries
Project Queries (7)
- List projects with filters
- Get my projects
- Get project tree structure
- Get project members
- Get project details
- Get project time plan
- List business lines
Reports & Statistics (5)
- Time statistics with grouping
- Time entry reports
- Project time reports
- Working days information
- Time entry warnings
📖 Usage Examples
After setting up, you can use natural language in Claude Desktop:
Please show me my time entries
List all projects
Search for user "John Doe"
Get time statistics for this week
Show me project details for project #123
🔧 Environment Variables
TIMESHEET_API_BASE_URL- API base URL (required)TIMESHEET_API_TOKEN- JWT token for authentication (required)MCP_TRANSPORT- Transport method (default: stdio)MCP_LOG_LEVEL- Logging level (default: INFO)
🛠️ Development
Clone the repository:
git clone https://github.com/yangyuezheng/ai-emp.git
cd ai-emp/timesheet-mcp-server-v2
Install dependencies:
pip install -r requirements.txt
Run tests:
python test_tools.py
📚 Documentation
📄 License
MIT License - see LICENSE file for details
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
📞 Support
- Issues: GitHub Issues
- Documentation: GitHub Docs
🙏 Acknowledgments
- FastMCP - MCP framework
- Model Context Protocol - Protocol specification
- Claude - AI assistant
Version: 2.0.0 Status: Production Ready ✅
Metadata
Release files for timesheet-mcp-server 2.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| timesheet_mcp_server-2.0.1.tar.gz | 39.4 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| timesheet_mcp_server-2.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 60.7 kB
Release files / timesheet_mcp_server-2.0.1.tar.gz
| Download URL | timesheet_mcp_server-2.0.1.tar.gz |
|---|---|
| Size | 39.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
113134b485fe4aa06bdd4ba8ee2fda81f86a1bca0c8e056da34cc60f8d789d73
|
|
BLAKE2b-256 checksum How to use checksums |
236a8a879232804342541830c0775efe87547cba1bb677c108a9c02ed28a9926
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / timesheet_mcp_server-2.0.1-py3-none-any.whl
| Download URL | timesheet_mcp_server-2.0.1-py3-none-any.whl |
|---|---|
| Size | 21.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
af24c3a4b987915e49d503d532198dcf316c90d8cfe86c5db66f44922aeef20b
|
|
BLAKE2b-256 checksum How to use checksums |
85b4ac16e15aa107c8101e65377acf4973f60f999445e0eba349a2fd7c0adf92
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for timesheet-mcp-server 2.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.