Early MCP Server
A Model Context Protocol server for the Early time tracking API, enabling natural language time tracking, activity management, and report generation.
README
Early MCP Server
A complete Model Context Protocol (MCP) server for Early (formerly Timeular) time tracking API v4.
Use natural language to track time, manage activities, generate reports, and more—directly from Claude.
Quick Start
1. Get API Credentials
- Go to Early Account Settings
- Scroll to the bottom to find the API section
- Generate your API Key and API Secret
2. Install
git clone https://github.com/weichselbaum/early-mcp.git
cd early-mcp
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
3. Configure Claude Desktop
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"early": {
"command": "/absolute/path/to/early-mcp/venv/bin/python",
"args": ["/absolute/path/to/early-mcp/early_mcp.py"],
"env": {
"EARLY_API_KEY": "your_api_key_here",
"EARLY_API_SECRET": "your_api_secret_here"
}
}
}
}
4. Restart Claude Desktop
The Early tools should now appear in Claude.
Usage Examples
Start tracking:
"Start tracking on LWX"
Check current timer:
"What am I working on?"
Stop with note:
"Stop tracking, note: finished feature implementation"
Log time manually:
"Log 2 hours on Meeting yesterday from 2pm to 4pm"
Weekly report:
"Show me my time report for last week"
Manage tags:
"Create a tag called 'urgent' in my Income folder"
Features
46 tools covering the complete Early API:
| Category | Tools | Description |
|---|---|---|
| User | 2 | Get current user, list team users |
| Tracking | 5 | Start, stop, edit, cancel, get current |
| Time Entries | 5 | List, get, create, edit, delete |
| Activities | 5 | List, create, edit, archive, unarchive |
| Folders | 10 | Full CRUD + member management |
| Tags | 4 | List, create, update, delete |
| Mentions | 3 | Create, update, delete |
| Leaves | 5 | Create, approve, deny, delete |
| Webhooks | 5 | List events, subscribe, unsubscribe |
| Reports | 2 | Generate report, today summary |
API Notes
Time Formats
All times use ISO 8601: 2024-01-15T14:30:00.000
Minimum Duration
Time entries require at least 1 minute duration.
Tags & Mentions in Notes
Special syntax for notes:
- Tags:
<{{|t|TAG_ID|}}> - Mentions:
<{{|m|MENTION_ID|}}>
Development
# Run locally
python early_mcp.py
# Test with MCP Inspector
npx @modelcontextprotocol/inspector python early_mcp.py
License
MIT - see LICENSE
API Documentation
The docs/ folder contains reference documentation for developers who want to understand the Early API or build custom implementations:
- EARLY_API_V4_REFERENCE.md - Markdown reference covering all endpoints, parameters, and response formats
- early_api_v4_collection.json - Full Postman collection export
How the docs were sourced
The JSON collection was exported from Early's official Postman workspace. Click "Run in Postman" (top right), fork the collection to your own workspace, then export as JSON. The collection is maintained by Timeular (Early's parent company).
Links
Roadmap
See ROADMAP.md for planned features and ideas. Feedback welcome!
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.