Is the server really read‑only?
Yes. Every tool is an inspection operation (`list_*`, `get_*`, `head_*`) and cannot create, modify, or delete any resource. This makes it safe for production accounts and unattended agent loops.
@ionos-cloud
基本信息
Inspect and manage IONOS CLOUD infrastructure via MCP
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ionoscloud": {
"command": "/path/to/ionoscloud-mcp",
"env": {
"IONOS_TOKEN": "your-api-token",
"IONOS_S3_ACCESS_KEY": "your-s3-access-key",
"IONOS_S3_SECRET_KEY": "your-s3-secret-key"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A read-only Model Context Protocol (MCP) server that connects your IONOS CLOUD account to any MCP‑compatible AI assistant or agent. It provides 112 tools across six IONOS CLOUD products for listing, inspecting, and auditing infrastructure through natural‑language prompts or programmatic loops. Built and maintained by the IONOS Cloud team, it runs as a local binary, in a CI runner, or inside a container.
Install via Homebrew (brew install ionos-cloud/ionos-cloud/ionoscloud-mcp), Docker, pre‑built binary, go install, or from source. Set the IONOS_TOKEN environment variable (and optionally IONOS_S3_ACCESS_KEY and IONOS_S3_SECRET_KEY for Object Storage). Add the server to your MCP client’s config JSON, then ask natural‑language questions about your infrastructure.
Yes. Every tool is an inspection operation (`list_*`, `get_*`, `head_*`) and cannot create, modify, or delete any resource. This makes it safe for production accounts and unattended agent loops.
The server runs as a Go binary (Go 1.25+ for builds) and is available as OCI images for linux/amd64 and linux/arm64. It requires an IONOS CLOUD account and an API token.
By default all tools register at startup (“eager” mode). Setting `IONOS_MCP_LOAD_MODE=lazy` registers Compute and Object Storage tools only on demand via two sentinel tools, which is useful for clients like Windsurf that have tool‑count limits.
Complete documentation, including per‑client setup guides, FAQ, and tutorials, is available at [docs.ionos.com/cloud/ai/mcp-server](https://docs.ionos.com/cloud/ai/mcp-server).
🚀 The fast, Pythonic way to build MCP servers and clients.

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Model Context Protocol Servers

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Open-source MCP to use Blender with any LLM
评论