How do I install the project?
Follow the steps in the Installation section. Make sure you have the required dependencies — Docker Desktop for Windows with the daemon exposed on `tcp://localhost:2375` without TLS.
@nideil
Basic information
Docker's MCP Server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"docker-mcp-stdio": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"freezeolo/docker-mcp-server"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The Docker MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with Docker Desktop on Windows, enabling advanced automation and interaction capabilities for developers and tools.
Install Docker Desktop for Windows and expose the daemon on tcp://localhost:2375 without TLS. Then configure the server in Claude Desktop by adding the provided JSON entry to mcpServers, which runs the Docker container freezeolo/docker-mcp-server via Docker CLI.
Follow the steps in the Installation section. Make sure you have the required dependencies — Docker Desktop for Windows with the daemon exposed on `tcp://localhost:2375` without TLS.
Docker Desktop for Windows is required. The server itself runs as a Docker container (`freezeolo/docker-mcp-server`) that communicates with the Docker daemon over HTTP.
The server connects to Docker Desktop via the daemon exposed on `tcp://localhost:2375` without TLS. You must enable this in Docker Desktop Settings > General.
Open `http://localhost:2375/version` in your browser. A JSON response with Docker version information confirms the setup is correct.
No authentication or special transport is mentioned. It uses standard HTTP to the Docker daemon and connects via the MCP stdio transport when launched through Claude Desktop.
Query MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.
Connect Supabase to your AI assistants
Deploy and manage SnapDeploy apps (Docker containers on AWS) from Claude Code, Cursor, Codex or Gemini CLI: builds, logs, env vars, add-ons, domains.
MCP server connecting to Kubernetes

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a
Comments