gcal-mcp
An MCP server for managing Google Calendar and Tasks with energy-aware scheduling and priority-based task management. It enables natural language interactions for creating flight or lodging events, managing reading queues, and optimizing daily schedules.
README
gcal-mcp
An MCP server for Google Calendar and Google Tasks, designed for use with Claude Code. Paste a flight confirmation, manage tasks with energy-aware scheduling, queue articles for reading — all through natural language.
What It Does
- Flight events — Paste a confirmation email, get a timezone-aware calendar event (
SFO → JFK | AA 1234) - Lodging events — Paste a booking confirmation, get 3 events: all-day stay span, timed check-in, timed check-out
- Reading queue — Save articles to read later, batch-schedule them into configurable morning reading slots
- Task manager — Create tasks with Eisenhower priority quadrants and energy levels, synced to Google Tasks
- Energy-aware scheduling — Define your daily energy profile; high-energy tasks get scheduled into your peak hours
- Daily planning — Get optimized schedule proposals, rearrange task blocks, set tickler reminders
Setup
1. Google Cloud Project
- Go to Google Cloud Console and create a new project
- Enable the Google Calendar API and Google Tasks API (APIs & Services > Library)
- Configure the OAuth consent screen:
- User type: External
- Add scopes:
https://www.googleapis.com/auth/calendarandhttps://www.googleapis.com/auth/tasks - Add your Google email as a test user
- Publishing status: leave as "Testing"
- Create OAuth credentials:
- Credentials > Create Credentials > OAuth client ID
- Application type: Desktop app
- Download the JSON file and save it as
credentials.jsonin the project root
2. Install & Build
git clone <this-repo>
cd gcal-mcp
npm install
npm run build
3. Authenticate
Run the one-time OAuth setup (this opens your browser):
npm run auth
You'll be redirected to Google to grant calendar and tasks access. After approving, the token is saved locally in data/token.json.
Note: If you're in Google's "Testing" mode, the refresh token expires after 7 days of inactivity. Just run
npm run authagain if that happens.
4. Register with Claude Code
Add to your ~/.claude/.mcp.json (global) or project-level .mcp.json:
{
"mcpServers": {
"gcal": {
"command": "node",
"args": ["/absolute/path/to/gcal-mcp/dist/index.js"]
}
}
}
Restart Claude Code. All tools should now be available.
Tools
Calendar
| Tool | Description |
|---|---|
create_flight_event |
Create a flight event from extracted confirmation details |
create_lodging_event |
Create 3 lodging events (stay span, check-in, check-out) |
list_events |
List all events for a given date |
Reading Queue
| Tool | Description |
|---|---|
queue_reading |
Save an article URL to the reading queue |
list_reading_queue |
Show all queued articles |
remove_reading |
Remove an article from the queue |
schedule_readings |
Batch-schedule queued articles into reading time slots |
Task Manager
| Tool | Description |
|---|---|
add_task |
Create a task with priority quadrant, energy level, and duration |
quick_add_task |
Create a task and schedule it in one call |
list_tasks |
List tasks with optional filters (quadrant, energy, status) |
update_task |
Update task fields |
complete_task |
Mark a task as done |
schedule_task |
Schedule a task into a free calendar slot |
create_tickler |
Set a reminder to revisit a task on a future date |
Scheduling
| Tool | Description |
|---|---|
suggest_schedule |
Propose an optimized daily schedule based on priorities and energy |
rearrange_schedule |
Clear and re-propose task blocks for a day |
set_energy_profile |
Define your daily energy windows (peak hours, low-energy times) |
Usage
Just tell Claude what you want in natural language:
Flights:
"Here's my flight confirmation: [paste email text]"
Lodging:
"Here's my Airbnb booking: [paste email text]"
Tasks:
"Add a task to review the Q3 report, it's urgent and important, high energy, about 45 minutes"
Scheduling:
"Suggest a schedule for tomorrow" "Schedule my pending tasks for today"
Reading:
"Save this article for later: https://example.com/article" "Schedule my reading queue"
Customization
Config file
Copy config.default.json to config.json to override settings:
cp config.default.json config.json
config.json is gitignored, so your personal settings won't be committed. Available options:
| Key | Default | Description |
|---|---|---|
readingWindows |
5:30 AM and 10:00 AM, 30 min each | Time slots for scheduled reading events |
Energy profile
Set your energy profile through the set_energy_profile tool. The default profile is:
| Time | Energy Level |
|---|---|
| 9:00 – 11:00 AM | High |
| 11:00 AM – 1:00 PM | Medium |
| 1:00 – 3:00 PM | Low |
| 3:00 – 5:00 PM | Medium |
| 5:00 – 6:00 PM | Low |
Your profile is saved in data/profile.json and persists across sessions.
Templates
Each template file has customizable constants at the top:
| File | What to customize |
|---|---|
src/templates/flight.ts |
Title format, color (default: Blueberry/blue) |
src/templates/lodging.ts |
Title format, color (default: Sage/green), check-in/out block duration |
src/templates/reading.ts |
Title format, color (default: Lavender/purple) |
src/templates/task.ts |
Title format, color (default: Banana/yellow) |
After modifying templates, rebuild with npm run build.
Project Structure
├── config.default.json # Default settings (tracked)
├── config.json # Your local overrides (gitignored)
├── credentials.json # OAuth client credentials (gitignored, you provide)
├── data/ # Runtime data (gitignored)
│ ├── token.json # OAuth refresh token
│ ├── reading-queue.json # Reading queue
│ ├── tasks-meta.json # Task metadata (quadrant, energy, scheduling)
│ └── profile.json # Energy profile
src/
├── index.ts # MCP server entry point, tool registration
├── config.ts # Config loader (defaults + local overrides)
├── auth.ts # OAuth2 flow + token management
├── auth-cli.ts # Standalone auth script for first-time setup
├── calendar.ts # Google Calendar API wrapper
├── reading-queue.ts # Reading queue persistence
├── tasks.ts # Google Tasks API wrapper
├── tasks-meta.ts # Local task metadata (quadrant, energy, scheduling)
└── templates/
├── flight.ts # Flight event formatting
├── lodging.ts # Lodging event formatting
├── reading.ts # Reading event formatting
└── task.ts # Task time block formatting
Google Calendar Event Colors
| colorId | Name | Used for |
|---|---|---|
"9" |
Blueberry (blue) | Flights |
"2" |
Sage (green) | Lodging |
"1" |
Lavender (purple) | Reading |
"5" |
Banana (yellow) | Task blocks |
"3" |
Grape (purple) | Tickler reminders |
Available colors: Lavender (1), Sage (2), Grape (3), Flamingo (4), Banana (5), Tangerine (6), Peacock (7), Graphite (8), Blueberry (9), Basil (10), Tomato (11).
License
MIT — see LICENSE.
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.