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 Pydantic AI?
Pydantic AI validates every Scaleway tool response against typed schemas, catching data inconsistencies at build time. Connect 3 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Scaleway integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Scaleway connection logic from agent behavior for testable, maintainable code
Scaleway in Pydantic AI
Scaleway and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Scaleway to Pydantic AI 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 Pydantic AI
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 Pydantic AI 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 Pydantic AI
Every tool call from Pydantic AI 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 Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Scaleway MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Wiktionary
2 toolsUniversal linguistic intelligence — get word definitions, etymologies, and examples via AI.

Flock
10 toolsManage team collaboration via Flock — send rich messages with FlockML, handle public channels and private groups, and search rosters directly from any AI agent.

AT&T 5G
9 toolsAccess Open Gateway 5G Network APIs -- Number Verify, Device Location, SIM Swap detection, Quality on Demand, and Network Slicing via AT&T.

Audienceful
10 toolsManage subscribers, custom fields, and email automations via Audienceful — orchestrate newsletters and campaigns directly via AI.
