Scaleway MCP server
mcpother officialio.github.scaleway/scaleway-mcp · v2.65.1
Scaleway MCP server for interacting with the Scaleway APIs
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
#!/usr/bin/env bash
# scaleway (io.github.scaleway/scaleway-mcp), recipe docker (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-scaleway.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec docker run --rm --name mcp-my-agent-scaleway -p 127.0.0.1:${PORT}:8000 --env-file /etc/mcp/my-agent.env scaleway/cli:2.65.1
[Unit]
Description=MCP server scaleway (toolset my-agent), generated by Hub
After=network-online.target docker.service
Wants=network-online.target
[Service]
Type=simple
User=mcp
Group=mcp
SupplementaryGroups=docker
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/scaleway
WorkingDirectory=/var/lib/mcp/scaleway
ExecStart=/opt/mcp/my-agent/bin/scaleway.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/scaleway
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
docker run --rm -p 127.0.0.1:8101:8000 scaleway/cli:2.65.1
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T02:16:32+00:00).
# Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
# cp .env.example .env # fill the ${VAR}s
# docker compose up -d && bash smoke.sh
# Remote servers are not here: clients reach them directly (see clients/).
name: mcp-my-agent
services:
scaleway:
image: scaleway/cli:2.65.1
ports:
- 127.0.0.1:8101:8000
restart: unless-stopped
x-note: 'CHANGE_ME: check the image''s README for its transport and port; this assumes streamable
HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command
instead.'
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T02:16:32+00:00).
# kubectl create namespace mcp
# kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
# kubectl apply -f kubernetes.yaml
# Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
# with auth in front before exposing any of them.
apiVersion: v1
kind: Namespace
metadata:
name: mcp
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: scaleway
namespace: mcp
labels: &id001
app: scaleway
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: scaleway
image: scaleway/cli:2.65.1
ports:
- containerPort: 8000
name: http
env: []
---
apiVersion: v1
kind: Service
metadata:
name: scaleway
namespace: mcp
spec:
selector:
app: scaleway
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T02:16:32+00:00).
# Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
# Each server under `servers` is one Deployment + Service; the keys after it configure
# upstream charts a worker verified.
servers:
scaleway:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: scaleway
image: scaleway/cli:2.65.1
ports:
- containerPort: 8000
name: http
env: []
# helm install my-agent helm/my-agent -n mcp
in the cloud
one click: the provider's deploy form opens filled in, in your own account- koyeb
-
Clients connect to the service's https://…koyeb.app address plus /mcp.
- azure
-
A Container Apps environment with one app per server, each with HTTPS ingress and one replica. The deployment's outputs list the endpoints.
connect to it
copy what your client needsdocker run -i --rm scaleway/cli:2.65.1
{
"mcpServers": {
"scaleway": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"scaleway/cli:2.65.1"
]
}
}
}
#!/usr/bin/env bash # Registers every server with Claude Code (run once; `claude mcp list` to check). set -euo pipefail set -a; [ -f .env ] && source .env; set +a claude mcp add scaleway -- docker run -i --rm scaleway/cli:2.65.1
{
"mcpServers": {
"scaleway": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"scaleway/cli:2.65.1"
]
}
}
}
{
"servers": {
"scaleway": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"scaleway/cli:2.65.1"
]
}
}
}
name: my-agent target: local servers: - hub: io.github.scaleway/scaleway-mcp
- not probed yet: tools unpinned, ingest lists them
tools
Probe result: faileddocker: the container exited: r/bin/scw --list-sub-commands List all subcommands -o, --output string Output format: json or human, see 'scw help output' for more info (default "human") -p, --profile string The config profile to use Use "/usr/bin/scw [command] --help" for more information about a command.
runs · 1
the latest tests of this entry by the hub and its workers, newest first| date | worker | method | status | sandbox | reason |
|---|---|---|---|---|---|
| 2026-10-17 13:37 | local-mac-vm | docker | failed | gvisor | docker: the container exited: r/bin/scw --list-sub-commands List all subcommands -o, --output string Output format: json or human, see 'scw help output' for mor… |