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.
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。