Connects to Azure's official updates RSS feed and exposes a single search tool that lets you filter by keyword, status (Preview, GA, Retired), category, date range, or GUID. The main use case is staying on top of Azure platform changes without manually checking the updates website. Ask it about new Kubernetes features, upcoming service retirements, or what's currently in preview. It includes faceted search to discover available product categories and tags. Built in Python, runs via uvx or pip, and works with Claude Desktop, Cursor, Claude Code, and Copilot CLI. Good for cloud architects and platform teams who need to track Azure deprecations and new capabilities as part of migration planning or platform monitoring.
mcp-name: io.github.jonnybottles/azure-updates
Stay up-to-date with Azure platform changes through AI-powered natural language queries. This Python-based MCP (Model Context Protocol) server connects AI assistants like Claude to Azure Updates, enabling you to search and filter Azure service announcements, feature releases, preview launches, and retirement notices—all through conversational queries.
Azure Updates MCP Server bridges the gap between Azure's official updates feed and your AI assistant, allowing you to:
Perfect for developers, cloud architects, and IT professionals who need to monitor Azure platform evolution, plan migrations, or stay informed about new capabilities—without manually checking the Azure updates website.
uvx (Recommended)If you are installing or running the server via uvx, you must have uv installed first.
uvx): https://github.com/astral-sh/uvInstall uv:
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
irm https://astral.sh/uv/install.ps1 | iex
Verify installation:
uv --version
uvx --version
uvxallows you to run the MCP server without installing the package globally.
If you prefer not to use uvx, you can install the package directly with pip.
pip install azure-updates-mcp
In this case, uv / uvx is not required.
uvx azure-updates-mcp
Or install with pip:
pip install azure-updates-mcp
uvx azure-updates-mcp@latest
Or with pip:
pip install --upgrade azure-updates-mcp
One-click setup: Click the VS Code badge for automatic configuration (requires
uvinstalled) Manual setup: See instructions below for Cursor, Claude Code, Copilot CLI, or Claude Desktop
include_facets=True to get taxonomy counts (product categories, products, tags, statuses). Use limit=0 with include_facets=True to discover available filter values.Once connected to an MCP client, you can ask questions like:
uvx azure-updates-mcp
Or if installed with pip:
azure-updates-mcp
Add to your Claude Desktop MCP config:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonUsing uvx (recommended)
{
"mcpServers": {
"azure-updates": {
"command": "uvx",
"args": ["azure-updates-mcp"]
}
}
}
Using installed package
{
"mcpServers": {
"azure-updates": {
"command": "azure-updates-mcp"
}
}
}
Option 1: One-Click Install (Recommended)
cursor://anysphere.cursor-deeplink/mcp/install?name=azure-updates-mcp&config=eyJjb21tYW5kIjogInV2eCIsICJhcmdzIjogWyJhenVyZS11cGRhdGVzLW1jcCJdfQ==
Option 2: Manual Configuration
Add to your Cursor MCP config:
~/Library/Application Support/Cursor/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json%APPDATA%\Cursor\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.jsonclaude mcp add --transport stdio azure-updates -- uvx azure-updates-mcp
Add to ~/.copilot/mcp-config.json:
{
"mcpServers": {
"azure-updates": {
"type": "stdio",
"command": "uvx",
"args": ["azure-updates-mcp"]
}
}
}
pytest
ruff check src/ tests/
MIT
silenceper/mcp-k8s
azure/containerization-assist
io.github.evozim/aws-builder
reza-gholizade/k8s-mcp-server
flux159/mcp-server-kubernetes