Scaleway MCP Server

create_instance

Create a new Scaleway compute instance with a specified name, type, and image. Optionally, set the zone and tags for the instance.

Instructions

Create a new compute instance.

Args: name: Name for the new instance instance_type: Instance type (e.g., DEV1-S, GP1-XS, PLAY2-NANO) image_id: Image ID to use for the instance zone: Scaleway zone (e.g., fr-par-1). If not provided, uses default zone. tags: Optional list of tags for the instance

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "instance_type": "<instance_type>",
      "image_id": "<image_id>"
    },
    "name": "create_instance"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes
`tags`	No
`zone`	No
`image_id`	Yes
`instance_type`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 2, 2026

TDQS

A3.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It only mentions that zone defaults if not provided and that tags are optional. It does not disclose mutation side effects, idempotency, authentication requirements, or provisioning behavior, leaving significant gaps for a create operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exceptionally concise and well-structured: a single opening line followed by a bullet-style list of parameters with brief explanations. No words are wasted, and the most critical information (what the tool does) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adequately documents the parameters and notes the default zone behavior, but lacks broader context such as how to obtain an image_id, what instance types are valid, or what happens after creation. With an output schema present, return values are covered, but usage context and behavioral details are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning beyond the bare schema by providing examples for instance_type and zone, explaining the zone default behavior, and noting tags are optional. While 'name' and 'image_id' descriptions are largely tautological, the overall coverage compensates for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb+resource combo 'Create a new compute instance,' which unambiguously identifies the tool's function and distinguishes it from sibling tools like list_instances, delete_instance, and start_instance. The purpose is explicit and matches the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage—when you want to create a new compute instance—but provides no explicit guidance on when to use this vs alternatives, no exclusions, and no prerequisites. It is a basic statement of intent rather than helpful contextual usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server