mcp

A command set for managing the MCP server that exposes Scaleway CLI commands as AI tools.

In plain words
What is it for?
It helps list available MCP resources and filter them by service area, resource type, or read-only access.
Why use it?
It helps you inspect which Scaleway operations can be made available to an AI assistant, especially read-only ones.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/scaleway/scaleway-cli/mcp
Clone the repo
git clone --depth 1 https://github.com/scaleway/scaleway-cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 979 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00979
Opus 5 $0.00000 $0.00490
Sonnet 5 $0.00000 $0.00196
Haiku 4.5 $0.00000 $0.00098

Measured yesterday against content hash b92a5ee02230, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/mcp.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation for scw mcp

Commands for managing the MCP server that exposes Scaleway CLI commands as AI tools.

MCP server management commands

Commands for managing the MCP server that exposes Scaleway CLI commands as AI tools.

List available MCP resources

Lists all CLI commands that would be exposed as MCP resources by the server. Resources are read-only endpoints for list commands that can be accessed via URI. Use filters to see which resources are available for specific namespaces or resources.

Usage:

scw mcp server list-resources [arg=value ...]

Arguments:

Name Description Argument Specifications
namespaces Filter by namespaces (e.g., instance, iam, object)
resources Filter by resources (e.g., server, volume, bucket)
read-only Only list read-only resources Default: false

Examples:

List all available MCP resources

scw mcp server list-resources

List resources for a specific namespace

scw mcp server list-resources namespaces=instance

List resources for a specific resource type

scw mcp server list-resources resources=server

List only read-only resources

scw mcp server list-resources read-only=true

List available MCP tools

Lists all CLI commands that would be exposed as MCP tools by the server. Use filters to see which commands are available for specific namespaces, resources, or verbs.

Usage:

scw mcp server list-tools [arg=value ...]

Arguments:

Name Description Argument Specifications
namespaces Filter by namespaces (e.g., instance, iam, object)
resources Filter by resources (e.g., server, volume, bucket)
verbs Filter by verbs (e.g., get, list, create)
read-only Only list read-only tools (get, list operations) Default: false

Read the full file on GitHub · 167 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 167 lines · 0 tokens per session scan A b92a5ee02230

Subscribe to this mod's changes

mcp is a command published in the GitHub repository scaleway/scaleway-cli (996 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 979 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.