MCP Azure runs on your own machine — the client starts it, so there is no endpoint to ping. 406 installs a week from npm. Last commit 30 Aug 2026.
Azure Resource Manager inventory & ops for AI agents — governed, confirmation-gated.
Today is the operative word: we check MCP Azure every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-azure -- npx -y @dockndevai/mcp-azure
{
"mcpServers": {
"mcp-azure": {
"args": [
"-y",
"@dockndevai/mcp-azure"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-azure]
command = "npx"
args = ["-y", "@dockndevai/mcp-azure"]
{
"mcpServers": {
"mcp-azure": {
"args": [
"-y",
"@dockndevai/mcp-azure"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-azure": {
"args": [
"-y",
"@dockndevai/mcp-azure"
],
"command": "npx"
}
}
}
Azure DevOps boards, repos, pipelines & projects for AI agents — governed.
Kubernetes MCP server for diagnosis, resource management, GitOps, and RBAC-enforced operations.
Query and manage Microsoft Graph and Azure Resource Manager APIs from MCP clients.
Verified cloud cost forecasting for AI agents. AWS, GCP, Azure pricing matrix.
Azure FinOps cost optimization for Claude Code: idle resources, rightsizing, reserved savings.
Verified cloud cost forecasting for AI agents. AWS, GCP, Azure pricing matrix.
Azure + GCP cost management: spending, forecasts, anomalies, budgets, idle resources, and tags.
Cloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks.
Answers built from our own checks of this server.