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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.