DockaShell

@anzax

About 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.

#agent #docker #mcp #model-context-protocol #vibe-coding #coding-agent

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dockashell": {
      "command": "dockashell",
      "args": [
        "serve"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is DockaShell?

DockaShell is an MCP (Model Context Protocol) server that gives AI agents isolated Docker containers to work in. Each agent gets its own persistent environment with shell access, file operations, and full audit trails.

How to use DockaShell?

Install globally with npm install -g dockashell, then run dockashell build, dockashell create my-project, and dockashell start my-project. Add the server to your MCP client configuration using command dockashell with args ["serve"]. Requires Node.js 20+ and Docker running.

Key features of DockaShell

Shell-based workflows instead of specialized tools
Container isolation for host system safety
Persistent workspace surviving across sessions
Complete audit trail for every command
Self-evolving agents building their own tools
Autonomous exploration without constant approval

Use cases of DockaShell

Data analysis with Python environment and CSV processing
Web development building React apps with live preview
Research assistant with persistent SQLite databases
Meta-learning by analyzing previous traces to improve

FAQ from DockaShell

What problems does DockaShell solve?

It addresses no persistent memory, tool babysitting, limited toolsets, and lack of self-reflection in current AI assistants.

How does it ensure security?

Each agent runs in an isolated Docker container, giving full autonomy inside with zero risk to the host system.

What are the requirements?

Node.js 20+ and a running Docker engine.

Can agents persist data across sessions?

Yes, each container uses a persistent volume so files, databases, and context survive between sessions.

Frequently asked questions

What problems does DockaShell solve?

It addresses no persistent memory, tool babysitting, limited toolsets, and lack of self-reflection in current AI assistants.

How does it ensure security?

Each agent runs in an isolated Docker container, giving full autonomy inside with zero risk to the host system.

What are the requirements?

Node.js 20+ and a running Docker engine.

Can agents persist data across sessions?

Yes, each container uses a persistent volume so files, databases, and context survive between sessions.

Comments

Basic information

More Other MCP servers

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K

XcodeBuildMCP

cameroncooke

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

6.0K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

MCP Go 🚀

mark3labs

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

8.9K

Unity MCP ✨

justinpbarnett

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

12.2K