Waldur MCP server enables integration between Waldur instances and Claude Desktop by implementing the Model Context Protocol (MCP). This server allows Claude to interact directly with your Waldur instance, providing AI assistance for your Waldur-managed resources and operations.
Install the Waldur MCP server using pip:
pip install waldur-mcp-server
Or using UV:
uv pip install waldur-mcp-server
Before configuring the server, you'll need to generate an API token:
Create or edit the Claude Desktop configuration file at the appropriate location for your operating system:
%APPDATA%\Claude\claude_desktop_config.json
~/Library/Application Support/Claude/claude_desktop_config.json
For published servers, add the following to your configuration file:
{
"mcpServers": {
"waldur-mcp-server": {
"command": "uvx",
"args": [
"waldur-mcp-server"
],
"env": {
"WALDUR_API_URL": "https://your-waldur-instance",
"WALDUR_TOKEN": "your-token"
}
}
}
}
For development or unpublished servers:
{
"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"
}
}
}
}
Remember to replace:
https://your-waldur-instance
with your actual Waldur instance URLyour-token
with the API token you generatedOn macOS, log files are located at:
~/Library/Logs/Claude/mcp.log
spawn uvx ENOENT
error: Ensure that your PATH environment variable includes the Python installation directory where uv
is installed. Alternatively, specify the full path to uvx
in the configuration file (e.g., ~/Library/Frameworks/Python.framework/Versions/3.13/bin/uvx
)
Invalid token: Verify that your token has the correct permissions and hasn't expired
Connection issues: Ensure that the WALDUR_API_URL is accessible from your machine
For more detailed debugging, use the MCP Inspector:
npx @modelcontextprotocol/inspector uv --directory C:\\waldur_service run waldur-mcp-server
When using the Inspector, you'll need to set the required environment variables. After launching, the Inspector will display a URL you can open in your browser to begin debugging.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.