MCP Scaleway Functions

Registre officiel Autres

Unofficial MCP Server for Scaleway Serverless Functions

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

OCI package docker.io/cyclimse/mcp-scaleway-functions:0.3.4
Claude Code
claude mcp add mcp-scaleway-functions -- docker run -i --rm docker.io/cyclimse/mcp-scaleway-functions:0.3.4
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "mcp-scaleway-functions": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "docker.io/cyclimse/mcp-scaleway-functions:0.3.4"
            ]
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. MCP Scaleway Functions
  2. Getting Started
  3. Configuration
  4. Available Tools
  5. Debugging
  6. Development

MCP Scaleway Functions

Model Context Protocol (MCP) server to manage and deploy Scaleway Serverless Functions using the Model Context Protocol standard.

[!CAUTION] This project is unofficial and not affiliated with or endorsed by Scaleway. Some small safety measures are in place to prevent the LLM from doing destructive actions, but they're not foolproof. Use at your own risk.

Getting Started

Download the latest release from the releases page or build it from source using Go.

Run the MCP server:

./mcp-scaleway-functions

By default, the MCP server runs with the SSE transport on http://localhost:8080, but you can also change it to use Standard I/O (stdio) transport via the --transport stdio flag.

Then, configure your IDE or tool of choice to connect to the MCP server. Here are some examples:

VSCode (sse example)

Add a new server configuration in your .vscode/mcp.json file:

{
    "servers": {
        "mcp-scaleway-functions": {
            "url": "http://localhost:8080",
            "type": "http",
        }
    },
}
Crush (stdio example)

Crush is an open-source coding agent that supports MCP. You can find more information about in the Crush repository.

Add a new server configuration in your ~/.config/crush/crush.json file:

{
  "$schema": "https://charm.land/crush.json",
  "mcp": {
    "scaleway-functions": {
      "type": "stdio",
      "command": "mcp-scaleway-functions",
      "args": ["--transport", "stdio"],
      "timeout": 600,
      "disabled": false
    }
  }
}

You can even use Crush with Scaleway Generative APIs by adding a new provider in the same ~/.config/crush/crush.json file:

{
  "mcp": {
    // ... see above ...
  },
  "providers": {
    "scaleway": {
      "name": "Scaleway",
      "base_url": "https://api.scaleway.ai/v1/",
      "type": "openai",
      // To fetch from environment variables, use the `$VAR_NAME` syntax.
      // Note: this key requires the "GenerativeApisModelAccess" permission.
      "api_key": "$SCW_SECRET_KEY",
      "models": [
        {
          "name": "Qwen coder",
          "id": "qwen3-coder-30b-a3b-instruct",
          "context_window": 128000,
          "default_max_tokens": 8000
        }
      ]
    }
  }
}

That's it 🎉! Have fun vibecoding and vibedevoopsing as you please.

Configuration

By default, the MCP server reads from the standard Scaleway configuration file located at ~/.config/scw/config.yaml.

Further configuration can be done via the Scaleway environment variables to configure the MCP server.

For instance, you can set a region to work in via the SCW_DEFAULT_REGION environment variable.

SCW_DEFAULT_REGION=nl-ams ./mcp-scaleway-functions

Available Tools

ToolDescription
create_and_deploy_function_namespaceCreate and deploy a new function namespace.
list_function_namespacesList all function namespaces.
delete_function_namespaceDelete a function namespace.
list_functionsList all functions in a namespace.
list_function_runtimesList all available function runtimes.
create_and_deploy_functionCreate and deploy a new function.
update_functionUpdate the code or the configuration of an existing function.
delete_functionDelete a function.
download_functionDownload the code of a function. This is useful to work on an existing function.
fetch_function_logsFetch the logs of a function.
add_dependencyAdd a dependency to a local function. Useful for dependencies that rely on native code and therefore need Docker to be installed.

Debugging

You can enable debug logging by using the --debug flag when starting the MCP server. This will log all requests and responses to/from the Scaleway API.

To configure the log level, use the --log-level flag (default is info). Available log levels are: debug, info, warn, error.

Logs are stored in the $XDG_STATE_HOME/mcp-scaleway-functions directory (usually ~/.local/state/mcp-scaleway-functions).

Development

Running tests:

go tool gotestsum --format testdox

Generating mocks:

go tool mockery

Questions fréquentes

Qu'est-ce que MCP Scaleway Functions ?

Unofficial MCP Server for Scaleway Serverless Functions

Comment installer MCP Scaleway Functions ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add mcp-scaleway-functions -- docker run -i --rm docker.io/cyclimse/mcp-scaleway-functions:0.3.4. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour MCP Scaleway Functions ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

MCP Scaleway Functions est-il open source ?

Oui. Son code est sur GitHub sous licence Unlicense.

Qui maintient MCP Scaleway Functions ?

Il est publié par cyclimse. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.