docker -plugin
Docker Desktop MCP Toolkit integration for Clawdbot - Access 23 MCP servers with 248 tools
claude mcp add --transport stdio tgambit65-docker-mcp-plugin docker mcp gateway run
How to use
This MCP server integrates Docker Desktop's MCP Toolkit into Clawdbot, exposing a broad set of Docker management capabilities through the MCP protocol. It automatically discovers and exposes tools for containers, images, volumes, networks, and Docker Compose, allowing you to list, inspect, start/stop containers, pull/build images, manage volumes and networks, and orchestrate services via docker-compose. You can invoke these tools through natural language or predefined tool calls in Clawdbot conversations, enabling seamless containerized workflows and development environments. Commonly used commands include listing containers, starting or stopping specific containers, pulling or building images, and managing compose services, all backed by the Docker MCP Toolkit for consistent, protocol-driven interactions.
How to install
Prerequisites:
- Docker Desktop installed with MCP Toolkit enabled
- Clawdbot installed (version >= 2026.1.23 recommended)
- Docker MCP Toolkit configured (comes with Docker Desktop)
Installation options:
From npm (recommended for easy updates):
clawdbot plugins install @clawdbot/docker-mcp
From source/archive:
# Clone or download this repository
git clone https://github.com/clawdbot/docker-mcp-plugin.git
# Install the plugin
clawdbot plugins install ./docker-mcp-plugin
Enable the plugin after installation:
clawdbot plugins enable docker-mcp
Configuration (in clawdbot.json):
{
"plugins": {
"entries": {
"docker-mcp": {
"enabled": true,
"config": {
"mcpCommand": "docker",
"mcpArgs": ["mcp", "gateway", "run"],
"enabledServers": [],
"timeout": 30000,
"debug": false
}
}
}
}
}
Optional: If you need to adjust behavior, modify the timeout or enable debug in the same config block.
Additional notes
Tips and common issues:
- Ensure Docker Desktop and the MCP Toolkit are available and running; verify with docker mcp --help to confirm MCP tooling is accessible.
- If you don’t see specific servers, check the enabledServers array in the plugin config or set debug to true to view discovery logs.
- If you encounter connection errors, verify the Docker daemon is running and there are no firewall rules blocking localhost connections used by MCP Toolkit.
- Use docker mcp catalog to discover available MCP servers/tools and docker mcp to list/discover capabilities.
- The plugin automatically exposes a wide range of tools (e.g., docker_container_list, docker_image_pull, docker_compose_up, etc.). You can reference the USAGE_EXAMPLES.md for detailed call formats and examples.
Related MCP Servers
podman
Model Context Protocol (MCP) server for container runtimes (Podman and Docker)
mcp-container-ts
This is a quick start guide that provides the basic building blocks to set up a remote Model Context Protocol (MCP) server using Azure Container Apps. The MCP server is built using Node.js and TypeScript, and it can be used to run various tools and services in a serverless environment.
better-notion
Markdown-first MCP server for Notion API - composite tools optimized for AI agents
openapi-to
Turns any OpenAPI/Swagger API into an MCP server. One MCP tool per endpoint, Streamable HTTP - for AI clients calling your REST API.
mcp-turso
MCP server for interacting with Turso-hosted LibSQL databases
harvest
MCP server for Harvest time tracking API - use with Claude Desktop and other AI assistants