Skip to content
mcp/harbor
Gemini CLI

cloudpulse for Gemini CLI

io.github.lhf552004/cloudpulse

Cross-cloud observability for AI agents. Covers AWS, GCP, Vercel, and Cloudflare.

client:Gemini CLI transport:stdio runtime:npm

Install cloudpulse in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "cloudpulse": {
      "command": "npx",
      "args": [
        "-y",
        "cloudpulse-mcp"
      ],
      "env": {
        "AWS_ACCESS_KEY_ID": "<AWS_ACCESS_KEY_ID>",
        "AWS_SECRET_ACCESS_KEY": "<AWS_SECRET_ACCESS_KEY>",
        "AWS_REGION": "<AWS_REGION>",
        "VERCEL_TOKEN": "<VERCEL_TOKEN>",
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>",
        "GOOGLE_CLOUD_PROJECT": "<GOOGLE_CLOUD_PROJECT>",
        "CLOUDFLARE_API_TOKEN": "<CLOUDFLARE_API_TOKEN>",
        "CLOUDFLARE_ACCOUNT_ID": "<CLOUDFLARE_ACCOUNT_ID>"
      }
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs

cloudpulse in other clients

cloudpulse MCP server