mcpField
S
Scaleway MCP server

Scaleway MCP server

Local
cli.scaleway.comCloud & Infra1.0kUpdated today
RepositoryVisit website

About Scaleway MCP server

The Scaleway MCP server is an MCP namespace built into the Scaleway CLI, started with scw mcp server serve. It converts Scaleway CLI commands into tools that MCP-compatible AI assistants can call. It reuses the CLI's configuration file and environment variables, which suits existing Scaleway CLI users.

Key features

  1. 01Exposes CLI commands as MCP tools
  2. 02Tool names follow the namespace_resource_verb pattern
  3. 03Reuses CLI configuration and environment variables
  4. 04Debug logging enabled through SCW_DEBUG
  5. 05Tool testing with the MCP Inspector

Use cases

  1. 01Listing instance servers or IAM users through an AI assistant
  2. 02Running Scaleway cloud resource commands from an MCP client

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "scaleway-scaleway": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "scaleway/cli:2.65.1"
      ]
    }
  }
}
Run commanddocker run -i --rm scaleway/cli:2.65.1

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ociscaleway/cli:2.65.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Server for Scaleway CLI

This namespace provides MCP (Model Context Protocol) server functionality, exposing Scaleway CLI commands as AI tools.

Usage

Starting the MCP Server
scw mcp server serve

This starts the MCP server over stdio, which can be connected to by MCP-compatible AI assistants.

Configuration

The MCP server uses the same configuration as the CLI:

  • Config file: ~/.config/scw/config.yaml or $SCW_CONFIG_PATH
  • Environment variables: SCW_ACCESS_KEY, SCW_SECRET_KEY, etc.
Available Tools

All CLI commands are exposed as MCP tools with the naming convention:

  • namespace_resource_verb (e.g., instance_server_list)

Examples:

  • instance_server_list - List servers
  • iam_user_list - List IAM users

Architecture

  • server/ - Core MCP server implementation
    • server.go - MCP server wrapper and tool registration
    • tool.go - Command-to-tool conversion and execution
    • schema.go - JSON Schema generation from ArgSpecs

Development

Testing
go test ./internal/namespaces/mcp/... -v
Debug Mode

Enable debug logging:

SCW_DEBUG=true scw mcp server serve
Tool

You can use MCP inspector to explore and test the available tools.

Example: Using with an MCP Client

Configure your MCP client to connect to the Scaleway CLI server:

{
  "mcpServers": {
    "scaleway": {
      "command": "scw",
      "args": ["mcp", "server", "serve"]
    }
  }
}

The client will then have access to all Scaleway CLI commands as tools.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.