cyclimse avatar

MCP Scaleway Functions

cyclimse/mcp-scaleway-functions

This unofficial server connects Claude to Scaleway's serverless function platform, letting you create namespaces, deploy functions, update code, fetch logs, and manage dependencies through conversation. It reads your standard Scaleway config from ~/.config/scw/config.yaml and supports all their runtimes. The author includes safety measures against destructive actions but warns they're not foolproof. You can run it over stdio or SSE transport. Reach for this when you want to manage Scaleway functions without leaving your editor or want an AI to handle deployment workflows. Works with VSCode, Crush, and other MCP-compatible tools. The download_function tool is handy for pulling existing code to work on locally.

GitHub stars
6
tools
11
transport
STDIO
last updated
Apr 12, 2026

Tools

11 tools

Public tool metadata for what this MCP can expose to an agent.

create_and_deploy_function_namespaceCreate and deploy a new function namespace.

Create and deploy a new function namespace.

No parameter schema in public metadata yet.

list_function_namespacesList all function namespaces.

List all function namespaces.

No parameter schema in public metadata yet.

delete_function_namespaceDelete a function namespace.

Delete a function namespace.

No parameter schema in public metadata yet.

list_functionsList all functions in a namespace.

List all functions in a namespace.

No parameter schema in public metadata yet.

list_function_runtimesList all available function runtimes.

List all available function runtimes.

No parameter schema in public metadata yet.

create_and_deploy_functionCreate and deploy a new function.

Create and deploy a new function.

No parameter schema in public metadata yet.

update_functionUpdate the code or the configuration of an existing function.

Update the code or the configuration of an existing function.

No parameter schema in public metadata yet.

delete_functionDelete a function.

Delete a function.

No parameter schema in public metadata yet.

download_functionDownload the code of a function. This is useful to work on an existing function.

Download the code of a function. This is useful to work on an existing function.

No parameter schema in public metadata yet.

fetch_function_logsFetch the logs of a function.

Fetch the logs of a function.

No parameter schema in public metadata yet.

add_dependencyAdd a dependency to a local function. Useful for dependencies that rely on native code and therefore need Docker to be installed.

Add a dependency to a local function. Useful for dependencies that rely on native code and therefore need Docker to be installed.

No parameter schema in public metadata yet.

Sponsors

Readme

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:


View the full README on GitHub

Details

Repository
github.com/cyclimse/mcp-scaleway-functions
Package
docker.io/cyclimse/mcp-scaleway-functions:0.3.4
Transport
STDIO
Registry
MCP registry, active