Timesheet MCP Server
Enables natural language control of the Timesheet API for timer management, task tracking, and project management through MCP tools.
README
Timesheet MCP Server
A Model Context Protocol (MCP) server that provides natural language access to the Timesheet API through standardized tools.
Features
- Timer Management: Start, stop, pause, and resume timers with natural language
- Task Enhancement: Add notes, expenses, and pauses to running tasks
- Project Management: Create, update, list, and delete projects
- Task Management: Full CRUD operations for tasks
- Natural Language Support: Use simple phrases to control your timer
Installation
Quick Start with npx
The easiest way to use the Timesheet MCP server is with npx (no installation required):
npx @timesheet/mcp
Global Installation
For frequent use, you can install globally:
npm install -g @timesheet/mcp
timesheet-mcp
Local Installation
For project-specific installation:
npm install @timesheet/mcp
Configuration
Using Environment Variables
Create a .env file with your API token:
TIMESHEET_API_TOKEN=your-api-token-here
Using Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"timesheet": {
"command": "npx",
"args": ["@timesheet/mcp-server"],
"env": {
"TIMESHEET_API_TOKEN": "your-api-token"
}
}
}
}
For a globally installed version:
{
"mcpServers": {
"timesheet": {
"command": "timesheet-mcp",
"env": {
"TIMESHEET_API_TOKEN": "your-api-token"
}
}
}
}
Sample Prompts
Timer Control
-
Start timer:
- "Start the timer for ProjectX"
- "Start timer for ProjectX 10 minutes ago"
- "Begin tracking time on the mobile app project"
-
Stop timer:
- "Stop the timer"
- "Stop working"
- "I'm done for the day"
-
Pause timer:
- "I have a break"
- "Pause the timer"
- "Taking lunch"
-
Resume timer:
- "Resume work"
- "Back from break"
- "Continue timer"
-
Check status:
- "What's my timer status?"
- "Am I tracking time?"
- "Show current timer"
Task Enhancements
-
Add notes:
- "Add a note: Fixed the login bug"
- "Note that I spoke with the client about requirements"
-
Add expenses:
- "Add expense: $45 for lunch with client"
- "Record taxi expense of $25"
-
Update task:
- "Update the description to 'Working on API integration'"
- "Mark current task as billable"
- "Add feeling rating of 4"
Project Management
-
List projects:
- "Show me all my projects"
- "List active projects"
- "What projects do I have?"
-
Create project:
- "Create a new project called 'Website Redesign'"
- "Add project 'Mobile App v2' with default billable tasks"
-
Update project:
- "Archive the old website project"
- "Rename project X to 'Client Portal'"
Task Management
-
List tasks:
- "Show today's tasks"
- "List all running tasks"
- "What did I work on yesterday?"
-
Create task:
- "Create a 2-hour task for ProjectX from 9am to 11am"
- "Log 4 hours on the API project for yesterday"
-
Update task:
- "Mark task X as paid"
- "Update task description"
- "Change task to non-billable"
Available Tools
Timer Operations
timer_start- Start timer for a projecttimer_stop- Stop the running timertimer_pause- Pause the timer (start break)timer_resume- Resume timer after breaktimer_status- Check current timer statustimer_update- Update running timer details
Task Enhancements
task_add_note- Add note to current tasktask_add_expense- Add expense to current tasktask_add_pause- Add manual pause to current task
Project Management
project_list- List all projectsproject_create- Create new projectproject_update- Update existing projectproject_delete- Delete project
Task Management
task_list- List tasks with filterstask_create- Create new tasktask_update- Update existing tasktask_delete- Delete task
Authentication
auth_configure- Set API authentication
Getting Your API Token
- Log in to your Timesheet account
- Go to Settings → API Access
- Generate a new API token
- Copy the token and add it to your configuration
Development
# Clone the repository
git clone https://github.com/timesheet/timesheet-mcp.git
cd timesheet-mcp
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build for production
npm run build
# Run tests
npm test
Troubleshooting
Timer not starting?
- Ensure you have a valid API token configured
- Check that the project ID exists in your account
- Verify you have permission to create tasks for the project
Authentication errors?
- Double-check your API token is correct
- Ensure the token hasn't expired
- Try generating a new token from your Timesheet settings
License
MIT
Support
For issues and feature requests, visit: https://github.com/timesheet/timesheet-mcp/issues
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.