Home / MCP / Waldur MCP Server

Waldur MCP Server

Connect Waldur with Claude Desktop via MCP to query and manage Waldur data from Claude.

python

2stars

View on GitHub

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
    "mcpServers": {
        "waldur_mcp": {
            "command": "uv",
            "args": [
                "--directory",
                "C:\\\\waldur_service",
                "run",
                "waldur-mcp-server"
            ],
            "env": {
                "WALDUR_API_URL": "https://your-waldur-instance",
                "WALDUR_TOKEN": "your-token"
            }
        }
    }
}

You can connect Waldur to Claude Desktop using the Waldur MCP Server. It implements the Model Context Protocol (MCP), letting Claude interact directly with your Waldur instance to perform actions and retrieve data in a structured, standardized way.

How to use

Set up the Waldur MCP Server and point Claude Desktop to it. You will run a local MCP server process that communicates with Waldur via the provided API token, then configure Claude Desktop to load that server as an MCP endpoint. Once connected, you can perform MCP-backed interactions such as querying Waldur data and triggering supported actions through Claude.

How to install

Prerequisites include Python 3.13 or higher and the uv package manager. You will also need access to a Waldur API URL and a generated API token.

Install the Waldur MCP server package with Python’s package manager, or install via uv afterward.

pip install waldur-mcp-server
```
```bash
uv pip install waldur-mcp-server

Additional steps

Generate a Waldur API token by logging into your Waldur instance, navigating to Username > Credentials > API Token, and creating a token with an appropriate lifetime. You will use this token in the MCP server configuration.

Configuration blocks

{
  "mcpServers": {
    "waldur_mcp": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        "C:\\waldur_service",
        "run",
        "waldur-mcp-server"
      ],
      "env": {
        "WALDUR_API_URL": "https://your-waldur-instance",
        "WALDUR_TOKEN": "your-token"
      }
    }
  }
}
```

```json
{
  "mcpServers": {
    "waldur_mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "waldur-mcp-server"
      ],
      "env": {
        "WALDUR_API_URL": "https://your-waldur-instance",
        "WALDUR_TOKEN": "your-token"
      }
    }
  }
}

Debugging and troubleshooting

On macOS, log files are located at ~/Library/Logs/Claude/mcp.log. If you encounter a spawn error, ensure that your PATH includes the Python directory where uv/uvx is installed, or specify the full path to uvx in the configuration. For the best debugging experience, use the MCP Inspector, which you can launch to observe the MCP flow and inspect messages.

Common issues include an invalid token (check permissions and expiration) and connection problems (verify that WALDUR_API_URL is accessible).

Notes on running and troubleshooting

MCP servers operate over stdio, so debugging can be nuanced. Prefer the MCP Inspector for live debugging, which provides a browser-based view of the MCP session and helps you observe requests and responses in real time.