


















Use Case
Use your AI client to systematically scan your IONOS CLOUD environment and identify misconfigurations before they turn into incidents.
Use Case
Give your finance and engineering teams a natural-language interface to IONOS CLOUD billing data—without writing a single line of code.
Use Case
Connect AI agents to IONOS CLOUD account data so they can operate based on the actual infrastructure status rather than static documentation.
No. This version is read-only by design—every tool performs only inspection and query operations. Nothing on the server can create, modify, or delete IONOS CLOUD resources, so connecting to live production accounts is safe.
The difference is crucial: API requests are sent directly from your device via HTTPS to @cloudBrand—with no third parties involved along the way. Your prompts and tool outputs are transmitted to your client’s AI model provider (e.g., Anthropic, Microsoft). For a fully EU-sovereign path, in which inference also remains within European infrastructure, combine the MCP Server with the IONOS CLOUD AI Model Hub.
Dedicated setup guides are available for Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Gemini CLI, JetBrains AI Assistant, Windsurf, Kiro, Continue, Cline, Zed, and OpenCode. Any other MCP-compliant client will also work, including AI agent frameworks such as the OpenAI Agents SDK and LangGraph.
Yes. The complete source code is available at github.com/ionos-cloud/ionoscloud-mcp under the Apache 2.0 license. You can see exactly what the server does, contribute, or report issues directly through GitHub.
Yes. Create a token with read-only access permissions for Compute Engine, Cloud DNS, Billing, and Object Storage. Since the server is read-only, a compromised token can only expose data—it cannot modify or delete resources.