MCP Server Docker
About
MCP Server Docker is a Model Context Protocol server that connects to a local Docker daemon, enabling MCP-compatible clients like Claude Desktop to interact with Docker. It automatically detects and uses the current Docker environment with no additional configuration.
Details
- Author
- milgelren
- Downloads
- 282
- Categories
- Cloud Service
Jump to
- Connects to a local Docker daemon automatically.
- Minimal setup using a single npx command.
- Works with any MCP-compatible client.
- Requires only a running Docker installation.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Server DockerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Usage with Claude Desktop
{
"mcpServers": {
"docker": {
"command": "npx",
"args": ["mcp-server-docker"]
}
}
}
The server will automatically connect to your current docker daemon. Make sure you have docker installed and running
run_command
Execute a command inside a Docker container service
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server docker": {
"docker": {
"command": "npx",
"args": [
"mcp-server-docker"
]
}
}
}
}McpServers
{
"docker": {
"command": "npx",
"args": [
"mcp-server-docker"
]
}
}MCP Server Docker
MCP Server that can connect to docker
Usage with Claude Desktop
{
"mcpServers": {
"docker": {
"command": "npx",
"args": ["mcp-server-docker"]
}
}
}
The server will automatically connect to your current docker daemon. Make sure you have docker installed and running
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
