DockaShell
DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit trail.
What is DockaShell?
DockaShell is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to dockashell is an mcp server that gives ai agents isolated docker containers to work in. mcp tools for shell access, file operations, and full audit trail.
DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit trail.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- DockaShell is an MCP server that gives AI agents isolated Do
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx dockashellConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use DockaShell
DockaShell is a Node.js MCP server that provisions isolated Docker containers as sandboxed workspaces for AI agents, giving them safe shell access, file operations, and a complete audit trail of every command and file change. Each project gets its own persistent Docker container, preventing agents from affecting the host system while retaining state across sessions. Developers using AI coding agents who need a safe, reproducible environment for running arbitrary code, installing packages, or testing scripts will use DockaShell to contain that activity.
Prerequisites
- Node.js 20+ installed on your system
- Docker Desktop (macOS/Windows) or Docker Engine (Linux) installed and running
- An MCP-compatible client such as Claude Desktop
- npm for global package installation
Install DockaShell globally
Install the dockashell package globally from npm so the CLI commands are available system-wide.
npm install -g dockashellBuild the base Docker image
Run dockashell build to pull and prepare the base container image that DockaShell uses for agent workspaces.
dockashell buildCreate and start a project container
Create a named project container that will serve as the agent's isolated workspace. The container persists between sessions.
dockashell create my-project
dockashell start my-projectConfigure Claude Desktop to use DockaShell
Add the DockaShell MCP server to your Claude Desktop config. It uses 'dockashell serve' as the stdio command.
{
"mcpServers": {
"dockashell": {
"command": "dockashell",
"args": ["serve"]
}
}
}Restart Claude Desktop and assign a project
Relaunch Claude Desktop. Tell Claude which DockaShell project container to use, then ask it to run commands or work on code inside the isolated environment.
DockaShell Examples
Client configuration
Full claude_desktop_config.json entry for DockaShell using the serve command.
{
"mcpServers": {
"dockashell": {
"command": "dockashell",
"args": ["serve"]
}
}
}Prompts to try
Tasks you can ask Claude to perform inside the isolated DockaShell container.
- "Use the my-project container to clone this git repo and run npm install"
- "Run the test suite inside the Docker container and show me the output"
- "Install Python 3.11 in the container and run this script"
- "List all files changed since the last git commit in the container workspace"
- "Create a simple Express server in the container, start it, and show me the logs"
- "Show me the full audit trail of commands run in the my-project container this session"Troubleshooting DockaShell
Docker daemon not running or connection refused
Ensure Docker Desktop (macOS/Windows) or Docker Engine (Linux) is started before running any dockashell commands. On Linux, run 'sudo systemctl start docker' and add your user to the docker group: 'sudo usermod -aG docker $USER' then log out and back in.
dockashell command not found after npm install
Ensure your npm global bin directory is in your PATH. Run 'npm bin -g' to find the location and add it to your shell profile (.zshrc or .bashrc). Alternatively use 'npx dockashell' as the command in your MCP config instead of 'dockashell'.
Container state lost between sessions
DockaShell uses persistent volumes for project containers. If state is lost, ensure you are using the same named project (dockashell start my-project) rather than creating a new one. Check 'docker ps -a' to see existing containers and their state.
Frequently Asked Questions about DockaShell
What is DockaShell?
DockaShell is a Model Context Protocol (MCP) server that dockashell is an mcp server that gives ai agents isolated docker containers to work in. mcp tools for shell access, file operations, and full audit trail. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install DockaShell?
Follow the installation instructions on the DockaShell GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with DockaShell?
DockaShell works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is DockaShell free to use?
Yes, DockaShell is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
DockaShell Alternatives — Similar Cloud Services Servers
Looking for alternatives to DockaShell? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up DockaShell in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use DockaShell?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.