Scribe
Enables AI assistants to securely manage Google Calendar events using natural language, including scheduling, rescheduling, deleting, and searching events.
README
✍️ Scribe: Google Calendar MCP Server
Scribe is a Model Context Protocol (MCP) server that allows CLI AI assistants (such as the Google Antigravity agy CLI or custom agents) to securely manage your Google Calendar schedule, events, and focus time using natural language.
🔌 Exposed MCP Tools
Once loaded by an AI client, Scribe registers the following tools:
list_events: View upcoming meetings and appointments.create_event: Schedule new events (supports summaries, descriptions, date-times, locations, and returns Smart Conflict Warnings if slots overlap).reschedule_event: Change the time range of an existing event ID (also returns Smart Conflict Warnings for overlaps).delete_event: Remove/cancel an event.search_events: Find appointments matching a free-text search query.find_free_slots: Scan a specific date and return a list of available open time slots.quick_add: Schedule events instantly using natural language parsing (e.g. "Lunch at 12pm tomorrow").
🛠️ Step-by-Step Setup
Step 1: Install Python Dependencies
Set up your python environment and install the required modules:
pip install -r requirements.txt
Step 2: Configure Google Cloud OAuth Client
Because Google Calendar requires secure authentication, you must configure a private Desktop OAuth Client in the Google Cloud Console:
- Open the Google Cloud Console.
- Create a new project (e.g.
Scribe-Calendar). - Search for Google Calendar API in the library search bar and click Enable.
- Go to the OAuth Consent Screen panel on the left sidebar:
- Select External user type and click Create.
- Enter your email under support and developer contacts.
- Under Test Users, click Add Users and add your own Google email address (so your private app can authenticate).
- Go to the Credentials panel on the left sidebar:
- Click Create Credentials -> OAuth Client ID.
- Select Desktop App as the Application Type.
- Name it (e.g.
Scribe-CLI) and click Create.
- Under the created Client ID row, click the Download icon on the far right to download the client secrets JSON.
- Save the downloaded JSON file directly into this
scribedirectory under the exact name:credentials.json
Step 3: Run the Authentication Script
Execute the authentication script to login and generate your offline access token:
./auth.py
A browser window will open asking you to authorize the application. Log in with the Google Account you added as a test user in Step 2. Once authorized, Scribe will save your session details locally in token.json.
Step 4: Link Scribe to Google Antigravity CLI
To enable your Antigravity agent to read and write to your calendar, add Scribe to your CLI settings file:
- Open the configuration file:
~/.gemini/antigravity-cli/settings.json - Add Scribe under the
mcpServerssettings block:{ "mcpServers": { "scribe": { "command": "python3", "args": ["/home/keen/Desktop/Projects and Codes/scribe/scribe_server.py"] } } }
🚀 Usage Examples
Start the Antigravity TUI or prompt agy directly:
- "Do I have any meetings tomorrow?"
- "Add a meeting with Sarah tomorrow at 10am for 1 hour about project launch"
- "Reschedule my focus time tomorrow afternoon to 3pm"
- "Cancel the lunch appointment on Friday"
📅 Timetable Importer (add_schedule.py)
Scribe includes a utility script to bulk import recurring university classes or recurring weekly schedules:
- Usage: Run the script locally once you are authenticated:
./add_schedule.py - Configuration: You can edit the classes list in
add_schedule.pyto change titles, days of the week, times, rooms, or instructors. - Semester Boundaries: Currently pre-configured to populate your 3rd Year 1st Semester from June 29th, 2026 to November 7th, 2026 with weekly recurrence rules.
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
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.
E2B
Using MCP to run code via e2b.