Cloudzero Model Context Protocol Server
local-only server
The server can only run on the client’s local machine because it depends on local resources.
Integrations
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.
Once 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 fromstart_date
toend_date
get_dimensions
for billing dimensionslist_budgets
to list budgetslist_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:
Generate your CloudZero API key.
Edit .env
with:
Install
To install the MCP server into Claude Desktop:
Edit 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
.
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:
This is useful for troubleshooting bugs in your code without having to continuously restart Claude Desktop.
This server cannot be installed
A server that allows users to query and analyze cloud cost data from Cloudzero using natural language through Large Language Models.