Name: Waldur MCP server
Author: waldur

LABSCO SUMMARY

Reporting against your own Waldur instance, in conversation.

It is a thin, self-hosted bridge — one package, two environment variables, and an API token whose lifetime and permissions you set. What it is documented for is the reporting question: what is deployed, what is being used, and what that means for the next decision.

What it is

Waldur's MCP server connects a Waldur instance to Claude Desktop, giving the assistant direct API access for reporting and deeper analysis of resource and usage data.

What you get

Your Waldur instance queried in conversation, for reporting and analysis of resources and usage
Direct API access that complements the llms.txt documentation files Waldur publishes
A published-package configuration through uvx, and a directory configuration for running from a checkout
Debugging through the MCP Inspector, launched with npx @modelcontextprotocol/inspector

Requirements

Python 3.13 or higher, the uv package manager, and the waldur-mcp-server package from pip or uv. Two environment variables carry the connection: WALDUR_API_URL and WALDUR_TOKEN. The token comes from Username > Credentials > API Token in your instance, with a lifetime you choose.

Setup effort

One command plus a key — pip install waldur-mcp-server, then supply credentials

See installation options

USE CASES

01

Pulling a usage report without building a query

Ask about resource and usage data on your instance and get the analysis back in the conversation you are already in.

02

Understanding what is actually deployed

Explore resources across the instance to inform a decision, instead of paging through the web interface.

03

Getting an assistant to reason about your deployment

Pair the live API access with Waldur's published llms.txt documentation so the assistant has both the concepts and your real numbers.

BEFORE YOU INSTALL

What to know first

Requires

Python 3.13 or higher
uv on PATH
WALDUR_TOKEN in your environment

INSTALLATION

Connect your client

Add the block to your client, or run the command directly.

Server setup

Configuration file

JSON

{
  "mcpServers": {
    "waldur-mcp-server": {
      "command": "uvx",
      "args": [
        "waldur-mcp-server"
      ],
      "env": {
        "WALDUR_API_URL": "https://<YOUR_WALDUR_INSTANCE>",
        "WALDUR_TOKEN": "<YOUR_WALDUR_TOKEN>"
      }
    }
  }
}

https://<YOUR_WALDUR_INSTANCE> is your Waldur instance's address, and <YOUR_WALDUR_TOKEN> is the API token you generate under Username > Credentials > API Token.

pip

TERMINAL

pip install waldur-mcp-server

Waldur MCP server