zeughaus-mcp
Allows executing commands in ephemeral containers with any combination of Nix packages from the NixOS/nixpkgs repository.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@zeughaus-mcprun python3 and curl to fetch https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
zeughaus-mcp
MCP Server - Agentic Workbench backed by Nixery.
Execute commands in ephemeral containers with any combination of Nix packages.
Installation
Docker (recommended)
Docker is the recommended installation method because it provides workspace isolation - the MCP server itself runs in a container with access only to your specified workspace directory.
docker run --rm -i \
-v /var/run/docker.sock:/var/run/docker.sock \
-v /path/to/workspace:/workspace \
-e NIXERY_REGISTRY_URL=nixery.zeughaus.dev \
-e HOST_WORKSPACE_ROOT=/path/to/workspace \
ghcr.io/gtarkin/zeughaus_mcp:latestuvx (alternative)
Note: When running via uvx, the MCP server has full access to the host system. Use Docker for better isolation.
uvx zeughaus-mcpRelated MCP server: mcp-omnienv-nix
Configuration
Environment variables:
Variable | Required | Default | Description |
| Yes | - | Nixery registry URL (see below) |
| Yes | - | Workspace path to mount into containers |
| No |
| Docker network mode |
| No |
| Container execution timeout |
Nixery Registries
Nixery is a Docker-compatible registry that builds container images on-the-fly from Nix packages.
Available Registries
Registry | Channel | Description |
| nixos-25.11 | Self-hosted instance for zeughaus-mcp (recommended) |
| nixos-unstable | Public Nixery instance by Google |
nixery.zeughaus.dev (Recommended)
The default registry for zeughaus-mcp. This is a self-hosted Nixery instance with:
Nix Channel:
nixos-25.11(stable packages)Source: github.com/NixOS/nixpkgs
Build timeout: 600 seconds
nixery.dev (Alternative)
The public Nixery instance maintained by Google. Use this if you prefer:
Nix Channel:
nixos-unstable(latest packages)No dependency on third-party infrastructure
To use the public registry, set:
NIXERY_REGISTRY_URL=nixery.devMCP Client Configuration
Claude Desktop (Docker - recommended)
{
"mcpServers": {
"zeughaus": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-v", "/var/run/docker.sock:/var/run/docker.sock",
"-v", "/path/to/workspace:/workspace",
"-e", "NIXERY_REGISTRY_URL=nixery.zeughaus.dev",
"-e", "HOST_WORKSPACE_ROOT=/path/to/workspace",
"ghcr.io/gtarkin/zeughaus_mcp:latest"
]
}
}
}Claude Desktop (uvx)
{
"mcpServers": {
"zeughaus": {
"command": "uvx",
"args": ["zeughaus-mcp"],
"env": {
"NIXERY_REGISTRY_URL": "nixery.zeughaus.dev",
"HOST_WORKSPACE_ROOT": "/path/to/workspace"
}
}
}
}License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Manage Sprites: sandboxed compute environments with exec, services, and checkpoints.
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…
Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.
Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables running arbitrary JavaScript code in isolated Docker containers with on-the-fly npm dependency installation, supporting both ephemeral one-shot executions and persistent sandbox environments.61 npm157-
- AlicenseBqualityDmaintenanceEnables creation of ephemeral, polyglot development environments using Nix for on-demand execution of code with specific dependencies across Python, Node.js, Ruby, R, and Lua without cluttering the system.2MIT
- AlicenseNot gradedqualityFmaintenanceAccess the Nix ecosystem (Nixpkgs, NixOS, Home Manager, nix-darwin, nixvim, nixhub...)7GPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to interact with NixOS development tools, manage builds, and optimize workflows through natural language.Apache 2.0