EverHour MCP Server
Enables AI assistants to interact with EverHour's API for time tracking, project management, task management, expense tracking, and reporting.
README
EverHour MCP Server
A Model Context Protocol (MCP) server for EverHour time tracking and project management integration. This server enables AI assistants to interact with EverHour's API for comprehensive time tracking, project management, task management, expense tracking, and reporting capabilities.
Features
🕐 Time Tracking
- Timer Management: Start, stop, and monitor active timers
- Time Records: Create, update, delete, and list time entries
- Time Reporting: Generate detailed time reports by project, user, or date range
📋 Project Management
- Project CRUD: Create, read, update, and delete projects
- Project Structure: Manage sections, labels, and project organization
- Budget Tracking: Set and monitor project budgets (time and money)
- Billing Configuration: Configure hourly rates and billing types
✅ Task Management
- Task Operations: Full CRUD operations for tasks
- Task Organization: Assign tasks to projects, sections, and users
- Task Estimates: Set and track time estimates
- Task Status: Manage open/closed status and progress
👥 User & Team Management
- User Profiles: Access user information and permissions
- Team Organization: Create and manage teams
- Role Management: Handle admin, supervisor, and member roles
💰 Client & Expense Management
- Client Management: Create and manage client information
- Expense Tracking: Record and categorize business expenses
- Invoice Integration: Prepare data for invoicing workflows
📊 Reporting & Analytics
- Time Summaries: Generate comprehensive time tracking reports
- Project Reports: Detailed project performance analytics
- User Reports: Individual productivity and time allocation reports
- Custom Filtering: Filter reports by date, project, user, or task
Installation
-
Clone and navigate to the directory:
git clone <repository-url> cd mcp-everhour -
Install dependencies:
npm install -
Get your EverHour API Key:
- Go to EverHour Settings
- Navigate to Settings → API
- Generate a new API key
- Copy the API key for configuration
-
Validate your API key (optional but recommended):
npm run auth "your_api_key_here"
Configuration
Environment Variables
Create a .env file in the project root:
# EverHour Configuration
EVERHOUR_API_KEY=your_everhour_api_key_here
# Server Configuration (optional)
PORT=6791
Alternative Configuration
You can also provide the API key during MCP initialization rather than using environment variables.
Usage
Development Mode
Start the EverHour MCP server in development mode:
npm run dev
The server will run on http://localhost:6791/mcp/everhour/
Production Mode
-
Build the project:
npm run build -
Start the server:
npm run start
Testing the Server
Test the server and verify available tools:
# Start the server in one terminal
npm run dev
# Test the server in another terminal
npm run test:server
MCP Client Configuration
Add the EverHour MCP server to your MCP client configuration:
{
"mcpServers": {
"everhour": {
"command": "npx",
"args": ["ts-node", "src/index.ts"],
"cwd": "/path/to/mcp-everhour",
"env": {
"EVERHOUR_API_KEY": "your_api_key_here"
}
}
}
}
Available Tools (38 total)
Authentication
set_api_key- Set the EverHour API key for authentication
User Management
get_me- Get current user profile informationlist_users- List all users in the workspaceget_user- Get specific user details by ID
Project Management
list_projects- List all projects with filtering optionsget_project- Get specific project detailscreate_project- Create a new projectupdate_project- Update existing projectdelete_project- Delete a project
Task Management
list_tasks- List tasks with comprehensive filteringget_task- Get specific task detailscreate_task- Create a new taskupdate_task- Update existing taskdelete_task- Delete a task
Time Tracking
list_time_records- List time records with date and project filtersget_time_record- Get specific time record detailscreate_time_record- Create a new time entryupdate_time_record- Update existing time recorddelete_time_record- Delete a time record
Timer Management
get_running_timer- Get currently running timerstart_timer- Start a timer for a specific taskstop_timer- Stop the currently running timer
Client Management
list_clients- List all clientsget_client- Get specific client detailscreate_client- Create a new clientupdate_client- Update existing clientdelete_client- Delete a client
Expense Management
list_expenses- List expenses with filteringcreate_expense- Create a new expense record
Reporting & Analytics
get_project_report- Get detailed project time reportget_user_report- Get detailed user time reportget_time_summary- Get time tracking summary with grouping
Project Structure
list_sections- List sections for a projectcreate_section- Create a new section in a projectlist_labels- List labels for projectscreate_label- Create a new label
Team Management
list_teams- List all teams in the workspacecreate_team- Create a new team
Example Usage
Testing the Server
Use the test script to verify the server is working:
npm run test:server
This will:
- Perform a health check
- Initialize with your API key
- List all available tools
- Test some basic API calls
Start a Timer
{
"tool": "start_timer",
"arguments": {
"task": "task_id_here",
"comment": "Working on feature implementation"
}
}
Create a Time Record
{
"tool": "create_time_record",
"arguments": {
"task": "task_id_here",
"time": 7200,
"date": "2024-01-15",
"comment": "Code review and testing"
}
}
List Projects
{
"tool": "list_projects",
"arguments": {
"status": "active",
"limit": 50
}
}
Create a Project
{
"tool": "create_project",
"arguments": {
"name": "Website Redesign",
"client": "client_id_here",
"type": "board",
"billing": {
"type": "project_hourly",
"rate": 75
},
"budget": {
"type": "time",
"budget": 144000
}
}
}
API Reference
Authentication
The EverHour MCP server uses API key authentication. The API key can be provided in two ways:
- Environment Variable: Set
EVERHOUR_API_KEYin your environment - MCP Initialization: Provide
api_keyparameter during MCP initialization
Error Handling
The server provides detailed error messages and codes:
AUTH_ERROR- Authentication failed or API key not providedINVALID_PARAMS- Required parameters missing or invalidHTTP_XXX- HTTP status code errors from EverHour APINETWORK_ERROR- Network connectivity issues
Rate Limiting
The server respects EverHour's API rate limits. If you encounter rate limiting, the server will return appropriate error messages.
Troubleshooting
Common Issues
-
Authentication Errors
- Verify your API key is correct
- Check that the API key has sufficient permissions
- Ensure you're using a valid, active API key
-
Network Errors
- Check your internet connection
- Verify EverHour's service status
- Check for firewall or proxy issues
-
Permission Errors
- Ensure your API key has the necessary permissions
- Contact your EverHour administrator for access rights
Debugging
Enable debug logging by setting the DEBUG environment variable:
DEBUG=everhour:* npm run dev
Testing API Key
Use the auth helper to validate your API key:
npm run auth "your_api_key_here"
This will test your API key and display available permissions and accessible data.
Available NPM Scripts
npm run dev- Start the server in development modenpm run build- Build the TypeScript projectnpm run start- Start the built servernpm run auth "api_key"- Test and validate your API keynpm run test:server- Test the running server and list tools
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License. See LICENSE file for details.
Support
For issues and questions:
- Check the EverHour API Documentation
- Review the troubleshooting section above
- Open an issue in this repository
Changelog
v1.0.0
- Initial release with comprehensive EverHour API coverage
- Full CRUD operations for projects, tasks, time records
- Timer management and time tracking
- Expense tracking and client management
- Reporting and analytics tools
- Team and user management features
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。