For the complete documentation index, see llms.txt. This page is also available as Markdown.

VS Code

The MCP server works with VS Code through GitHub Copilot's MCP support in agent mode.

Prerequisites

  • VS Code with the GitHub Copilot extension (version 0.22 or later)

  • The ionoscloud-mcp binary built and available. For more information, see Quick Start

  • An IONOS CLOUD API token. For least-privilege access, see Authentication to scope the token to only the tools you need.

Add the MCP server

Create or edit .vscode/mcp.json in your workspace. The "type": "stdio" field tells VS Code to run the server as a local process communicating over standard input/output; just enter it as shown:

{
  "servers": {
    "ionoscloud": {
      "type": "stdio",
      "command": "/usr/local/bin/ionoscloud-mcp",
      "env": {
        "IONOS_TOKEN": "your-api-token"
      }
    }
  }
}

To also enable Object Storage tools, add your Object Storage credentials:

For a user-wide configuration that applies to all workspaces, open VS Code settings (Ctrl+Shift+P > Open User Settings JSON) and add the same servers block under the key "mcp".

Verify the connection

1

Open Copilot Chat in agent mode

Open Copilot Chat and switch to Agent mode using the mode selector in the Copilot Chat panel.

2

Test the connection

Type: List my IONOS CLOUD data centers.

If Copilot responds that it cannot access that information, check Troubleshooting.

Note: All tools are registered at startup by default, so Compute Engine and Object Storage tools appear immediately. To reduce the startup tool count (for example, on clients with a tool-count cap), set IONOS_MCP_LOAD_MODE=lazy in the env block and call the ionos_load_compute_tools or ionos_load_objectstorage_tools sentinels on demand. For more information, see Selective Tool Loading.

For full VS Code MCP documentation, see Add and manage MCP servers in VS Code.

Last updated

Was this helpful?