Developer · Local MCP server

Cloudscope

Azure + GCP cost management: spending, forecasts, anomalies, budgets, idle resources, and tags.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.alexpota/cloudscope
Version
0.3.3
Status
Active
Category
developer
Transport
stdio (local process)
Package
npm
Published
2026-05-29
Updated
2026-05-29
Publisher
alexpota (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/alexpota) · how
Listed under
Azure MCP servers, Weather MCP servers, Google Cloud MCP servers
Repository
github.com/alexpota/cloudscope-mcp
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npmcloudscope-mcp0.3.3stdioAZURE_SUBSCRIPTION_ID, AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET (secret), GOOGLE_CLOUD_PROJECT, GCP_BILLING_TABLE, GCP_PROJECT_ID, GCP_BILLING_ACCOUNT_ID, GOOGLE_APPLICATION_CREDENTIALS (secret)

How to connect Cloudscope

Cloudscope runs locally from a Node.js package published to the npm registry: cloudscope-mcp version 0.3.3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y cloudscope-mcp@0.3.3. It reads these environment variables: AZURE_SUBSCRIPTION_ID, AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET (secret), GOOGLE_CLOUD_PROJECT, GCP_BILLING_TABLE, GCP_PROJECT_ID, GCP_BILLING_ACCOUNT_ID and GOOGLE_APPLICATION_CREDENTIALS (secret); set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "cloudscope": {
      "command": "npx",
      "args": [
        "-y",
        "cloudscope-mcp@0.3.3"
      ],
      "env": {
        "AZURE_SUBSCRIPTION_ID": "<value>",
        "AZURE_TENANT_ID": "<value>",
        "AZURE_CLIENT_ID": "<value>",
        "AZURE_CLIENT_SECRET": "<secret>",
        "GOOGLE_CLOUD_PROJECT": "<value>",
        "GCP_BILLING_TABLE": "<value>",
        "GCP_PROJECT_ID": "<value>",
        "GCP_BILLING_ACCOUNT_ID": "<value>",
        "GOOGLE_APPLICATION_CREDENTIALS": "<secret>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
CloudPepperManage CloudPepper servers, Odoo instances, backups, and deployments over MCP.Remote · HTTPLive check: sign-in requiredmcp.cloudpepper.io
CloudpriceCompare on-demand compute + storage pricing across AWS, Azure, and GCP. Bulk workload compare.Local · stdioPyPI: cloudprice-mcp
CloudpulseCross-cloud observability for AI agents. Covers AWS, GCP, Vercel, and Cloudflare.Local · stdionpm: cloudpulse-mcp
CloudQuellAsk about AWS, Azure, GCP, OpenAI, Anthropic and Snowflake costs, budgets, and anomalies.Remote · HTTPLive check: sign-in requiredmcp.cloudquell.com
CloudwrightCloud architecture and migration planning with costs, controls, evidence, and deployable IaC.Local · stdioPyPI: cloudwright-ai-mcp
CLS++ MemoryCross-LLM persistent memory: store context once, recall it from any AI model.Remote & Local · HTTP, stdioLive check: sign-in requiredclsplusplus.com
CludePortable agent memory anchored on Solana. Local SQLite + vector recall, open export.Local · stdionpm: @clude/sdk
CmsUXBERT Labs headless CMS: model, write and publish bilingual content, media, delivery checks.Remote · HTTPLive check: sign-in requiredcms-mcp.uxbert.ai