skylight
MCP server for Skylight family calendar - enables AI assistants to manage calendars, chores, lists, meals, and rewards
claude mcp add --transport stdio theeaglebyte-skylight-mcp npx @eaglebyte/skylight-mcp \ --env SKYLIGHT_EMAIL="your_email@example.com" \ --env SKYLIGHT_FRAME_ID="your_frame_id" \ --env SKYLIGHT_PASSWORD="your_password"
How to use
The Skylight MCP server enables AI assistants to interact with your Skylight Calendar API, exposing tools to read and manage calendar events, chores, lists, tasks, family information, and rewards. Once configured, you can query calendars for specific dates, view and create chores, inspect grocery or to-do lists, add tasks, fetch family members and devices, and check reward points. The server exposes a set of structured tools (get_calendar_events, get_lists, create_task, get_family_members, get_rewards, etc.) that your AI can call to perform actions on Skylight resources. It also provides clear guidance in the instructions for using the server, such as evaluating dynamic dates, defaulting grocery items to the main list, and noting that some features may require a Skylight Plus subscription.
To use it, configure the MCP server with your Skylight credentials and frame ID, then instruct your AI to call the available tools. For example, you can ask the AI to retrieve today’s calendar events, add a dishwashing chore for tomorrow, or fetch your current reward points balance. Before assigning chores, you can call get_family_members to learn member names, and you can rely on the tools to manipulate the appropriate Skylight resources.
How to install
Prerequisites:
- Node.js 18+ installed on your system
- Access to a Skylight account with an active subscription
- Your Skylight Frame ID
Option 1 — Install via npm package (recommended):
- Create or edit the mcp.json file in your project and add:
{
"mcpServers": {
"skylight": {
"command": "npx",
"args": ["@eaglebyte/skylight-mcp"],
"env": {
"SKYLIGHT_EMAIL": "your_email@example.com",
"SKYLIGHT_PASSWORD": "your_password",
"SKYLIGHT_FRAME_ID": "your_frame_id"
}
}
}
}
- Install dependencies and run the MCP server via your preferred runner:
npm install
- Start the server (depends on your setup, typically in your orchestrator):
npx @eaglebyte/skylight-mcp
Option 2 — Install from source:
- Clone the repository and install:
git clone https://github.com/TheEagleByte/skylight-mcp.git
cd skylight-mcp
npm install
- Build if required:
npm run build
- Run the server using Node (example path to built entry):
node dist/index.js
Notes:
- If you use the node-based path, include the same environment variables in your runtime environment.
- Update the mcp.json example for your actual environment before running.
Additional notes
Environment variables and configuration:
- SKYLIGHT_EMAIL / SKYLIGHT_PASSWORD: Use your Skylight credentials if you choose the email/password authentication path (recommended).
- SKYLIGHT_FRAME_ID: Required; the household/frame identifier for your Skylight setup.
- SKYLIGHT_TOKEN / SKYLIGHT_AUTH_TYPE: Alternative manual token authentication path is supported if you opt out of email/password. Ensure SKYLIGHT_FRAME_ID is provided in both cases.
Tips:
- Grocery items default to the main grocery list if no list is specified.
- Dates can be provided as today, tomorrow, day names, or YYYY-MM-DD.
- Some tools (rewards, meals, photos) may require a Skylight Plus subscription.
- Use get_family_members before assigning chores to learn member names.
Common issues:
- Misconfigured credentials or missing frame ID will prevent authentication; verify environment variables.
- If using npx with a package name, ensure network access and npm registry availability.
- When running locally, ensure Node.js 18+ is in PATH and that your environment variables are exported to the process running the MCP server.
Related MCP Servers
server-google-news
【Star-crossed coders unite!⭐️】Model Context Protocol (MCP) server implementation providing Google News search capabilities via SerpAPI, with automatic news categorization and multi-language support.
gtm
An MCP server for Google Tag Manager. Connect it to your LLM, authenticate once, and start managing GTM through natural language.
architect
A powerful, self-extending MCP server for dynamic AI tool orchestration. Features sandboxed JS execution, capability-based security, automated rate limiting, marketplace integration, and a built-in monitoring dashboard. Built for the Model Context Protocol (MCP).
google-search-console
It connects directly to your Google Search Console account via the official API, letting you access key data right from AI tools like Claude Desktop or OpenAI Agents SDK and others .
agentsource -ext
Access live company and contact data through Explorium's MCP server
Email MCP server with full IMAP + SMTP support — read, search, send, manage, and organize email from any AI assistant via the Model Context Protocol