Compatible with every major AI agent and IDE
What is the Scaleway MCP Server?
Connect your Scaleway account to any AI agent to manage your cloud infrastructure through natural language. This server provides direct access to the Scaleway Instances API.
What you can do
- Instance Discovery — List all virtual machines across different availability zones (e.g., fr-par-1, nl-ams-1)
- Provisioning — Create new instances by specifying names, commercial types (like DEV1-S), and image IDs
- Power Management — Remotely power on, power off, or reboot your servers
- Lifecycle Control — Terminate instances that are no longer needed directly from the chat
How it works
- Subscribe to this server
- Enter your Scaleway Secret Key
- Start managing your cloud resources from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps Engineers — quickly check server status or reboot instances without leaving the terminal or IDE
- Developers — spin up new development environments using simple text commands
- Cloud Architects — audit active resources across multiple zones efficiently
Built-in capabilities (3)
Create a new Scaleway instance (server)
List Scaleway instances (servers) in a specific zone
Perform an action on a Scaleway instance (e.g., poweron, poweroff)
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 3 tools from Scaleway through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Scaleway, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Scaleway in OpenAI Agents SDK
Scaleway and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Scaleway to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Scaleway in OpenAI Agents SDK
The Scaleway MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 3 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Scaleway for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Scaleway MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I see my servers in a specific region like Paris?
Use the list_instances tool and provide the zone parameter (e.g., 'fr-par-1'). The agent will return a list of all instances currently provisioned in that specific Scaleway zone.
Can I reboot or shut down a server using this integration?
Yes! The perform_instance_action tool allows you to send 'poweron', 'poweroff', 'reboot', or 'terminate' commands to any specific server ID within a zone.
What information is needed to create a new instance?
To use create_instance, you need to provide the zone, a name for the server, the commercial type (e.g., 'DEV1-S'), and the image ID or label you wish to deploy.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Bybit
10 toolsAccess real-time crypto market data — tickers, klines, orderbook, trades, funding rates and open interest.

Corrently Energy
12 toolsAccess German energy market data — GrünstromIndex, CO₂ forecasts, solar predictions, electricity prices, and optimized scheduling for smart energy consumption.

Tango
12 toolsDocument any process by recording your screen clicks and turning them into step-by-step guides with annotated screenshots.

OpenSearch Vector
6 toolsRun k-NN vector searches on OpenSearch — create indexes, upsert embeddings, query similar documents, and manage your vector store from any AI agent.
