Scaleway MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCW_ACCESS_KEY | Yes | Scaleway access key | |
| SCW_PROJECT_ID | Yes | Scaleway project ID | |
| SCW_SECRET_KEY | Yes | Scaleway secret key | |
| SCW_DEFAULT_ZONE | No | Default zone | fr-par-1 |
| SCW_DEFAULT_REGION | No | Default region | fr-par |
| SCW_ORGANIZATION_ID | Yes | Scaleway organization ID |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_instancesA | List all compute instances in a Scaleway zone. Args: zone: Scaleway zone (e.g., fr-par-1, nl-ams-1). If not provided, uses default zone. |
| get_instanceA | Get detailed information about a specific instance. Args: instance_id: The ID of the instance to retrieve zone: Scaleway zone (e.g., fr-par-1). If not provided, uses default zone. |
| create_instanceA | 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 |
| start_instanceA | Start a stopped instance. Args: instance_id: The ID of the instance to start zone: Scaleway zone (e.g., fr-par-1). If not provided, uses default zone. |
| stop_instanceA | Stop a running instance. Args: instance_id: The ID of the instance to stop zone: Scaleway zone (e.g., fr-par-1). If not provided, uses default zone. |
| delete_instanceA | Delete an instance. Args: instance_id: The ID of the instance to delete zone: Scaleway zone (e.g., fr-par-1). If not provided, uses default zone. |
| list_private_networksA | List all private networks in a Scaleway region. Args: region: Scaleway region (e.g., fr-par, nl-ams). If not provided, uses default region. |
| create_private_networkA | Create a new private network. Args: name: Name for the new private network region: Scaleway region (e.g., fr-par, nl-ams). If not provided, uses default region. tags: Optional list of tags for the network |
| list_k8s_clustersA | List all Kubernetes clusters in a Scaleway region. Args: region: Scaleway region (e.g., fr-par, nl-ams). If not provided, uses default region. |
| get_k8s_clusterA | Get detailed information about a Kubernetes cluster. Args: cluster_id: The ID of the cluster to retrieve region: Scaleway region (e.g., fr-par, nl-ams). If not provided, uses default region. |
| list_imagesA | List available instance images. Args: zone: Scaleway zone (e.g., fr-par-1). If not provided, uses default zone. arch: Filter by architecture (x86_64 or arm64). If not provided, shows all. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool clearly targets a distinct resource and action (e.g., list vs get vs create for instances, separate tools for private networks and K8s). No two tools appear to do the same thing.
All tool names follow a consistent verb_noun pattern with lowercase and underscores (e.g., list_instances, create_private_network, get_k8s_cluster). There are no mixed conventions or vague verbs.
With 11 tools, the server is well-scoped, covering multiple resource types (instances, networks, K8s, images) without being overwhelming. Each tool serves a clear purpose.
Instance management is fairly complete (create, read, delete, start, stop), but private networks lack get/update/delete, and K8s clusters only have list/get with no create or delete. These are notable gaps that could hinder full workflows.