About My MCP Servers
My MCP Servers is a collection of Python MCP servers for calendar, weather, macOS music controls, and Azure Cosmos DB. It gives MCP clients access to these separate services, with Cosmos DB credentials loaded from Azure Key Vault.
Key features
- 01Google Calendar event management
- 02Location-based forecasts and weather alerts
- 03macOS Music playback controls
- 04Retrieve Cosmos DB documents by ID
Use cases
- 01Create or list calendar events and recurring meetings
- 02Check local forecasts and weather alerts
- 03Control playback in the macOS Music app
- 04Fetch a document from an Azure Cosmos DB container
MCP support
Provides MCP services for calendar, weather, macOS Music playback, and Azure Cosmos DB document retrieval.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMy MCP Servers
A collection of custom MCP (Model Context Protocol) servers providing various services including calendar management and weather information.
For more information about building MCP servers, see the official MCP documentation.
Features
- Calendar Service: Integration with Google Calendar API for event management
- Weather Service: Weather information and forecasting capabilities
- Sound Control Service: Basic playback controls for the Music app on macOS
- Cosmos DB Service: Retrieve documents from Azure Cosmos DB containers
System Requirements
- Python 3.10 or higher
- MCP SDK 1.2.0 or higher
- Google Calendar API credentials (
credentials.json)
Environment Setup
- Install uv (MacOS/Linux):
curl -LsSf https://astral.sh/uv/install.sh | sh
Note: Restart your terminal after installing uv to ensure the command is available.
- Clone the repository:
git clone <your-repository-url>
cd my-mcp-servers
- Sync your environment:
uv sync
- Test if it's working:
uv run weather/weather.py
Configuration
- Place your Google Calendar API credentials in
credentials.json- To obtain your credentials, follow the Google Calendar API Python Quickstart Guide Note: The authentication token will be automatically generated on first use of the calendar service.
Services
Calendar Service
The calendar service provides integration with Google Calendar, allowing you to:
- Create and manage calendar events
- List upcoming events
- Set up recurring meetings
Weather Service
The weather service offers:
- Weather forecasts
- Weather alerts
- Location-based weather information
Sound Control Service
This service exposes simple playback controls for macOS. It can:
- Play or pause the current track
- Skip to the next track
- Return to the previous track
Cosmos DB Service
The Cosmos DB service connects to Azure Cosmos DB and allows retrieval of
documents by their id. Connection information is securely loaded from an Azure
Key Vault secret during initialization.
Usage
Initialize the service with your Azure resources:
keyvault_name: Your Azure Key Vault name (e.g., "my-keyvault")secret_name: Name of the secret containing your Cosmos DB connection stringdatabase_name: Target Cosmos DB database namecontainer_name: Target container name within the database
Example initialization:
# The service will automatically connect using DefaultAzureCredential
# Ensure your environment has proper Azure authentication configured
await initialize(
keyvault_name="my-company-keyvault",
secret_name="cosmos-connection-string",
database_name="production-db",
container_name="documents"
)
Once initialized, you can retrieve documents by ID:
# Retrieve a document by its ID
document = await get_document_by_id("user-123")
License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.