cloud-tools runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 31 Aug 2026.
Multi-cloud cost, inventory and waste analysis over MCP: AWS, GCP, Cloudflare and OVH.
Today is the operative word: we check cloud-tools 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 cloud-tools -- npx -y @munhq/cloud-tools
{
"mcpServers": {
"cloud-tools": {
"args": [
"-y",
"@munhq/cloud-tools"
],
"command": "npx"
}
}
}
[mcp_servers.cloud-tools]
command = "npx"
args = ["-y", "@munhq/cloud-tools"]
{
"mcpServers": {
"cloud-tools": {
"args": [
"-y",
"@munhq/cloud-tools"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"cloud-tools": {
"args": [
"-y",
"@munhq/cloud-tools"
],
"command": "npx"
}
}
}
Cross-cloud observability for AI agents. Covers AWS, GCP, Vercel, and Cloudflare.
FinOps MCP: query allocated, correlated cloud and AI cost across AWS, GCP, Azure and Snowflake.
Cloud replacement for mcp-server-filesystem — 20 tools for S3, Azure Blob, and GCS
Cloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks.
Read-only AWS cost analysis: find idle and underutilized resources, with evidence.
Secure Umami Analytics MCP server for Cloud and self-hosted deployments
Compare, estimate, and deploy cloud infrastructure across AWS, GCP, and Azure for AI agents.
Multi-account Gmail on a Cloudflare Worker you deploy yourself: read, send, reply, labels, threads
Answers built from our own checks of this server.