scaleway-mcp
A comprehensive MCP server for the Scaleway cloud platform, enabling AI agents to inspect and manage cloud infrastructure through 155+ tools across compute, storage, networking, and platform services.
README
scaleway-mcp
A comprehensive Model Context Protocol (MCP) server for the Scaleway cloud platform. It exposes Scaleway's products as MCP tools so an AI agent (Claude Desktop, Claude Code, Cursor, and any other MCP client) can inspect and manage your cloud infrastructure.
- 21 products, 155+ tools spanning compute, containers, storage, databases,
networking, messaging, and platform services — built on the official
scaleway-asyncSDK. - Namespaced tools (
instances_list_servers,object_storage_list_buckets) so the agent can discover capabilities per product. - Safe by default. Destructive operations are opt-in and, when enabled, only touch resources this server created.
- Structured JSON output, not formatted text, so agents parse results reliably.
- One small file per product, with a documented recipe for adding more.
Beta. The tool surface may change. Review the security model before pointing it at a production account.
Quick start
The server runs with uv / uvx and needs a
Scaleway API key.
Claude Code
claude mcp add scaleway \
-e SCW_ACCESS_KEY=SCWXXXXXXXXXXXXXXXXX \
-e SCW_SECRET_KEY=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx \
-e SCW_DEFAULT_PROJECT_ID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx \
-- uvx scaleway-mcp
Claude Desktop / Cursor / other clients
Add to the client's MCP config (for Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"scaleway": {
"command": "uvx",
"args": ["scaleway-mcp"],
"env": {
"SCW_ACCESS_KEY": "SCWXXXXXXXXXXXXXXXXX",
"SCW_SECRET_KEY": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"SCW_DEFAULT_PROJECT_ID": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
}
}
}
Full client instructions: docs/adding-to-your-agent.md.
Authentication
The server authenticates exactly like the scw CLI and the official SDK: it
reads ~/.config/scw/config.yaml when present and overlays the standard
environment variables (SCW_ACCESS_KEY, SCW_SECRET_KEY,
SCW_DEFAULT_PROJECT_ID, SCW_DEFAULT_REGION, SCW_DEFAULT_ZONE, ...). If you
already use the CLI, it works with no extra setup. See
docs/configuration.md.
Product coverage
| Bundle | Products |
|---|---|
| Compute & Containers | Instances, Elastic Metal, Kubernetes (Kapsule), Serverless Containers, Serverless Functions, Container Registry |
| Storage & Databases | Object Storage (S3), Block Storage, Managed Databases (RDB), Redis |
| Networking | VPC, Load Balancers, Public Gateway, Domains & DNS, Flexible IP |
| Platform & Ops | IAM, Secret Manager, Cockpit (observability), Billing & Account |
| Messaging & Queuing | Queues (SQS), Topics & Events (SNS) |
The complete, always-current tool list with parameters is in
docs/TOOLS.md. Ask the agent to call scaleway_list_products
to see what is enabled at runtime.
Enable only the products you need:
SCW_ENABLED_PRODUCTS=instance,object_storage,rdb
Safety
- Reads and creates by default; deletes are opt-in. Delete tools are not
even registered unless
SCW_ENABLE_DELETE=true. - Resources created through this server are tagged
created_by=scaleway-mcp. With deletes enabled, the server refuses to delete anything lacking that tag unlessSCW_ALLOW_DELETE_UNTAGGED=true. - Use a least-privilege IAM key scoped to the products you enable. Details in docs/security.md.
Local development
git clone https://github.com/sndpl/scaleway-mcp
cd scaleway-mcp
uv sync --extra dev
uv run pytest # tests
uv run ruff check . # lint
uv run mypy # types
# Run against your account from a local checkout:
uvx --from . scaleway-mcp
Contributing
Adding a Scaleway product is a small, mechanical task. See CONTRIBUTING.md for the step-by-step recipe.
License
Apache-2.0. This is an unofficial, community project and is not affiliated with or endorsed by Scaleway.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。