MCP Server
The IONOS CLOUD MCP Server connects your AI client or AI agent to your IONOS CLOUD account using the Model Context Protocol (MCP). It runs as a local binary on your machine and makes API calls directly to IONOS CLOUD, not through any AI provider. It provides access to 100+ tools across Compute Engine, Managed Kubernetes, , Cloud DNS, Certificate Manager, Billing, and Activity Log.
Why IONOS CLOUD MCP
Read-only by default: Out of the box, these tools are inspection-only. The server cannot create, modify, or delete any resource. This makes it safe to connect to production accounts and share with teams. Write tools exist but must be enabled deliberately, and every create, delete, and disruptive action needs a two-step confirmation. For more information, see Write Operations.
Local binary: IONOS CLOUD API calls go directly from the MCP server to IONOS CLOUD. They are not proxied through Anthropic, Microsoft, or any third-party relay. The AI client sends tool outputs to its model backend for inference; review your AI client's privacy policy for details.
100+ tools across 7 products: Compute Engine, Managed Kubernetes, IONOS CLOUD Object Storage, Cloud DNS, Billing, Certificate Manager, and Activity Log.
Open source (Apache 2.0): Inspect the source, contribute, or extend at github.com/ionos-cloud/ionoscloud-mcp.
Pairs with the IONOS CLOUD Documentation MCP: Add
https://docs.ionos.com/cloud/~gitbook/mcpto your config to give your AI assistant live account data and full product documentation in the same session. For more information, see Overview.Discoverable on the major MCP registries: Available on the Official MCP Registry, Smithery, mcp.so, Glama, the Cursor Directory, mcpservers.org, PulseMCP, MCPMarket, and awesome-mcp-servers so you can find and install it from within your AI client.
Product Overview
Quick Links
Developer Tools
Supported products
50 read, 69 write
List and inspect data centers, servers, volumes, NICs, LANs, load balancers, NAT gateways, security groups, and more. With write tools enabled, also create, update, and delete them
8 read, 8 write
List and inspect Kubernetes clusters, node pools, nodes, and available versions. With write tools enabled, also create, scale, upgrade, and delete them
23
List buckets and objects, inspect bucket configuration (CORS, encryption, lifecycle, replication), and check access keys
Supported AI clients
Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, Gemini CLI, Kiro, JetBrains AI Assistant, Continue, Zed, Cline, OpenCode, and any other MCP-compatible client.
FAQ
Last updated
Was this helpful?