What it does for you
Lets your AI operate AWS — inspect resources, check bills, manage services, doing cloud ops through chat (spans AWS's official MCP suite).
Capabilities
- Query AWS resources and status
- View cost and billing
Once installed, try asking your AI
Say this directly in Claude / Cursor or any client with this server connected
- ›“How much did AWS cost this month? Which service is most expensive?”
Before you connect
Config example (to connect)
{
"mcpServers": {
"awslabs-core-mcp-server": {
"command": "uvx",
"args": [
"awslabs.core-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "ERROR"
}
}
}
}Install / Connect
# No npm package — install from source.
# See the repo's README for the exact command:
# https://github.com/awslabs/mcpFollow the official README; env and args vary per server.
🛠️ Maintenance weight 30% · 84 pts
📊 Adoption weight 25% · 70 pts
✅ Usability weight 20% · 20 pts
❤️ Health & community weight 25% · 76 pts
Sources: GitHub API · updated 2026-07-30
90-day trend
⭐ stars +0%
Similar / alternative servers
How to choose among these
Cloud/ops servers map to your platform — pick the official server for whatever cloud/tool you use.
- Monitoring / observability→Grafana (dashboards) · Dynatrace (root-cause)
- IaC / deploy→Terraform (IaC) · Cloud Run / Netlify / Heroku (deploy)
- Cloud cost (FinOps)→Vantage — multi-cloud cost analysis
ai.dinglebear/unraid-rmcp
Unraid RMCP
ai.dinglebear/arcane-rmcp
Arcane RMCP
azure-devops-mcp
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to
dev.servonaut/servonaut
Servonaut
One email a week, 5 minutes to see what happened in the MCP ecosystem
New servers, breakout trends, abandonment alerts — tracked automatically, curated by hand, sent to your inbox.
One email a week · unsubscribe anytime · no data selling