Cloudability Api Server MCP Server

@eelzinaty

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

eelzinaty

提交者

Issam AlZinati

关于 Cloudability Api Server MCP Server

A comprehensive Model Context Protocol (MCP) server for the Cloudability API, providing advanced cost management, Kubernetes container analytics, and budget forecasting capabilities

#kkubernetes#ibm #finops#cloudability

Cloudability Api Server MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "cloudability": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "main.py"
      ],
      "cwd": "/path/to/cloudability-mcp-server",
      "env": {
        "CLOUDABILITY_API_URL": "https://api.cloudability.com/v3",
        "CLOUDABILITY_ENVIRONMENT_ID": "your-environment-id",
        "CLOUDABILITY_DEFAULT_VIEW_ID": "12345",
        "CLOUDABILITY_KEY_ACCESS": "your-public-key",
        "CLOUDABILITY_KEY_SECRET": "your-private-key",
        "CLOUDABILITY_FRONTDOOR_URL": "https://frontdoor.apptio.com/service/apikeylogin"
      }
    }
  }
}

Cloudability Api Server MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Cloudability Api Server?

Cloudability Api Server is a Model Context Protocol (MCP) server that wraps the Cloudability API, providing advanced cost management, Kubernetes container analytics, and budget forecasting capabilities. It is intended for teams managing cloud costs and containerized workloads across AWS, Azure, GCP, IBM, and OCI.

How to use Cloudability Api Server?

Clone the repository, install dependencies with uv sync, copy the .env.example to .env and set Cloudability credentials (API URL, environment ID, and optionally Frontdoor API keys), then run uv run python main.py. Configure your MCP client to point to the server with the uv run python main.py command and appropriate environment variables.

Key features of Cloudability Api Server

Container cost allocation, provisioning, analytics, and label discovery
Cost reporting with 15 dimensions and 8 metrics
Budget lifecycle management with forecasting and alerts
Current month spending estimates and multi-month predictive forecasts
Vendor account listing for AWS, Azure, GCP, IBM, OCI
Flexible authentication: Bearer token, Frontdoor API keys, or Basic auth
Multi-region support: US, EU, APAC, ME
Resource caching with configurable TTL (default 15 minutes)

Use cases of Cloudability Api Server

Allocate Kubernetes container costs by namespace, workload, or label
Manage cloud budget lifecycles and receive forecast alerts
Generate current-month spending estimates with service-level breakdowns
Retrieve vendor accounts from multiple cloud providers for cost analysis
Build custom cost reports with advanced filtering and grouping

常见问题

What are the runtime requirements?

Python 3.14+ and the `uv` package manager. You also need Cloudability API access (Bearer token, API key, or Frontdoor API keys).

How does authentication work?

Three methods: 1) Frontdoor API keys automatically acquire an apptio‑opentoken when set in environment variables; 2) Bearer token with a manually provided apptio‑opentoken; 3) Legacy Basic auth with an API key.

What tools does the server expose?

Tools for container management (provision cluster, get deployment YAML, containers report, resource usage, label discovery, cluster info), budgets (list, get, get spending estimate), forecasts, and vendor account listing (AWS, Azure, GCP, IBM, OCI).

Is there rate limiting?

Yes. The `get_spending_estimate` tool is rate‑limited to 10 requests per user per minute and 20 per organization per minute.

Can I use the server in different regions?

Yes. Configure `CLOUDABILITY_API_URL` and `CLOUDABILITY_FRONTDOOR_URL` for US, EU, APAC, or ME regions, each with their own endpoints.

开发工具分类下的更多 MCP 服务器

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

BetterBugs

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.