cloudzero-mcp
Talk to your cloud data using CloudZero API and Model Context Protocol (MCP) server for LLM tool calling
Documentation
Cloudzero Model Context Protocol (MCP) server
Talk to your cloud cost data in Cloudzero from a Large Language Model (LLM).
Ask questions about your cost data such as plotting a month over month difference:

How it works
Uses CloudZero v2 API and the Model Context Protocol MCP.
graph LR
%%{init: {'theme':'neutral'}}%%
%% Define nodes
A[MCP Host]
B[Local MCP Server]
C[CloudZero API]
D[(Cloud Costs Data)]
%% Define connections
A -->|JSON-RPC 2.0| B
B -->|HTTP/JSON| C
C D
subgraph CloudZero_SaaS
C
D
end
subgraph Background_process
B
end
subgraph Claude_Desktop
A
end
subgraph Local_Machine
Claude_Desktop
Background_process
end
%% Define styles
classDef client padding:10px
classDef server padding:10px
classDef api padding:10px
classDef db padding:10px
%% Apply styles
class A client
class B server
class C api
class D dbOnce the MCP server is configured in Claude Desktop, it will be launched as a background process at
startup. Claude Desktop as the MCP Host will send an `initiatize` request to the MCP Server. The
server responds with its capabilities, which includes `prompts` and `tools` for tool calling.
The server implements several tools specific to CloudZero:
- `get_costs` to get billing data from `start_date` to `end_date`
- `get_dimensions` for billing dimensions
- `list_budgets` to list budgets
- `list_insights` to list insights
The MCP protocol uses JSON-RPC 2.0 for requests and responses.
Setup
Install Claude Desktop:
Install uv
Setup the project dependencies:
uv init
uv syncGenerate your CloudZero API key.
Edit `.env` with:
CLOUDZERO_API_KEY=YOUR_SECRET_KEYInstall
To install the MCP server into Claude Desktop:
uv run mcp install server.pyEdit your `claude_desktop_config.json` to set the proper path to the `uv` command and update your `USERNAME` as below.
This config file can be located in Claude Desktop under `Settings > Developer > Edit Config`.
"CloudZero": {
"command": "/Users/USERNAME/.local/bin/uv",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"/Users/USERNAME/workspace/open_source/cloudzero-mcp/server.py"
]
}Restart Claude Desktop. When the Desktop starts, it will launch the server process in the background.
You may see errors, and can drill into the logs to see what the problem is.
If no errors, try asking "what tools are available for cloud billing" to see it listed.

See Claude Desktop MCP documentation for more info.
Debug
For debugging, you can run the MCP development server with an interactive GUI to inspect:
uv run mcp dev server.pyThis is useful for troubleshooting bugs in your code without having to continuously restart Claude Desktop.

Frequently asked questions
What is cloudzero-mcp?
cloudzero-mcp is Talk to your cloud data using CloudZero API and Model Context Protocol (MCP) server for LLM tool calling
How do I install cloudzero-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is cloudzero-mcp open source?
Yes — it is hosted on GitHub at https://github.com/burkestar/cloudzero-mcp and has 3 stars.
Related MCP tools
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to
🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。 for the Model Context Protocol. Enhance AI assistants with po
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP