zeughaus-mcp
Execute commands in ephemeral containers with any combination of Nix packages.
README
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:latest
uvx (alternative)
Note: When running via uvx, the MCP server has full access to the host system. Use Docker for better isolation.
uvx zeughaus-mcp
Configuration
Environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
NIXERY_REGISTRY_URL |
Yes | - | Nixery registry URL (see below) |
HOST_WORKSPACE_ROOT |
Yes | - | Workspace path to mount into containers |
DOCKER_NETWORK_MODE |
No | host |
Docker network mode |
CONTAINER_TIMEOUT_SECONDS |
No | 300 |
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 |
|---|---|---|
nixery.zeughaus.dev |
nixos-25.11 | Self-hosted instance for zeughaus-mcp (recommended) |
nixery.dev |
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.dev
MCP 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.