Cloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks.
registry version 1.49.1
Python
uvx cloud-finops-mcpPython
uvx cloud-finops-mcp@1.49.1Streamable HTTP
https://mcp.optimnow.io/mcp
Pick your client — the config below is generated for this server (both local and hosted-endpoint forms). Copy respects the “Pin version” switch above.
claude_desktop_config.json
{
"mcpServers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp"
]
}
}
}{
"mcpServers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp@1.49.1"
]
}
}
}Remote (hosted) endpoint
https://mcp.optimnow.io/mcp
Claude Desktop: Settings → Connectors → Add custom connector, paste this URL.
Format verified against the official Claude Desktop docs ↗.
terminal
claude mcp add cloud-finops -- uvx cloud-finops-mcp
claude mcp add cloud-finops -- uvx cloud-finops-mcp@1.49.1
terminal
claude mcp add --transport http cloud-finops https://mcp.optimnow.io/mcp
Format verified against the official Claude Code docs ↗.
.cursor/mcp.json
{
"mcpServers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp"
]
}
}
}{
"mcpServers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp@1.49.1"
]
}
}
}.cursor/mcp.json (hosted endpoint)
{
"mcpServers": {
"cloud-finops": {
"url": "https://mcp.optimnow.io/mcp"
}
}
}Format verified against the official Cursor docs ↗.
.vscode/mcp.json
{
"servers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp"
]
}
}
}{
"servers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp@1.49.1"
]
}
}
}.vscode/mcp.json (hosted endpoint)
{
"servers": {
"cloud-finops": {
"type": "http",
"url": "https://mcp.optimnow.io/mcp"
}
}
}Format verified against the official VS Code docs ↗.
mcp_config.json
{
"mcpServers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp"
]
}
}
}{
"mcpServers": {
"cloud-finops": {
"command": "uvx",
"args": [
"cloud-finops-mcp@1.49.1"
]
}
}
}mcp_config.json (hosted endpoint)
{
"mcpServers": {
"cloud-finops": {
"serverUrl": "https://mcp.optimnow.io/mcp"
}
}
}Format verified against the official Windsurf docs ↗.
⭐ 61 stars · 最近更新于 29 天前
Cloud FinOps Skill & MCP Open source FinOps knowledge skill and MCP server for AI agents Claude, ChatGPT, Gemini, Cursor, and any MCP compatible client. Cloud cost optimisation across AWS, Azure, GCP and OCI, AI cost management and inference economics, Kubernetes, data platforms, allocation, chargeb…
Summary from the project README — github.com/OptimNow/cloud-finops-skills
Distributed as Python, Streamable HTTP, listed under Cloud & Infrastructure. Review our MCP security guide before granting access to real data.
Cloud FinOps Skill & MCP Open source FinOps knowledge skill and MCP server for AI agents Claude, ChatGPT, Gemini, Cursor, and any MCP compatible client. Cloud cost optimisation across AWS, Azure, GCP and OCI, AI cost management and inference economics, Kubernetes, data platforms, allocation, chargeb
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/OptimNow/cloud-finops-skills. Any third-party service it calls may require its own API key and account.
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Publish this server? Link back with a badge on your README or site — copy either snippet.
Markdown
[](https://mcpnav.net/server/cloud-finops/)
HTML
<a href="https://mcpnav.net/server/cloud-finops/"><img src="https://mcpnav.net/badge/cloud-finops.svg" alt="Listed on MCPNav" height="20"></a>