mcpField
W
Waldur MCP server

Waldur MCP server

Local
github.com/waldurCloud & Infra3Updated 40w ago
Repository

About Waldur MCP server

Waldur MCP server connects a Waldur instance to MCP-compatible clients. It uses an API token for authentication and lets clients interact with Waldur directly.

Key features

  1. 01Connect to a Waldur instance
  2. 02Configure access with an API token
  3. 03Install with pip or uv
  4. 04Client setup and debugging guidance

Use cases

  1. 01Connect Waldur to Claude Desktop
  2. 02Configure token-based access to a Waldur instance
  3. 03Debug the server with MCP Inspector

MCP support

Implements MCP to connect a Waldur instance to MCP clients, allowing them to interact with Waldur directly.

#waldur#mcp-server#cloud-platform

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Waldur MCP server

Waldur MCP server enables integration between Waldur instance and Claude Desktop by implementing the Model Context Protocol (MCP). This allows Claude to interact with your Waldur instance directly.

Quickstart

  1. Install Claude Desktop for your platform from the Claude Desktop releases page

  2. Install Python 3.13 or higher.

  3. Install uv package manager.

Installation

To install the package:

pip install waldur-mcp-server

Or with uv:

uv pip install waldur-mcp-server
Generate Waldur Token
  1. Log in to your Waldur instance
  2. Navigate to Username > Credentials > API Token
  3. Generate a new token with appropriate token lifetime - you'll need it for configuration
Claude Desktop MCP Server Configuration

On Windows: %APPDATA%\Claude\claude_desktop_config.json

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration 
{
  "mcpServers": {
    "waldur-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\waldur_service",
        "run",
        "waldur-mcp-server"
      ],
      "env": {
        "WALDUR_API_URL": "https://your-waldur-instance",
        "WALDUR_TOKEN": "your-token"
      }
    }
  }
}
Published Servers Configuration 
{
  "mcpServers": {
    "waldur-mcp-server": {
      "command": "uvx",
      "args": [
        "waldur-mcp-server"
      ],
      "env": {
        "WALDUR_API_URL": "https://your-waldur-instance",
        "WALDUR_TOKEN": "your-token"
      }
    }
  }
}
Debugging

On macOS, log files are located at ~/Library/Logs/Claude/mcp.log

If you encounter a spawn uvx ENOENT error, verify that your PATH environment variable includes the Python installation directory where uv is installed. Alternatively, you can specify the full path to uvx in the configuration file, for example: ~/Library/Frameworks/Python.framework/Versions/3.13/bin/uvx

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory C:\\waldur_service run waldur-mcp-server

When debugging, you'll need to set the required environment variables. Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Common issues
  • Invalid token: Verify token permissions and expiration
  • Connection issues: Check WALDUR_API_URL is accessible

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.