
Docker Mcp
io.github.alisaittekePublished by GitHub account alisaittekev0.2.4Updated Oct 24, 2026
MCP server for managing Docker containers, images, networks, volumes, and registries
The publisher's own server: Docker Recipes
Overview
Local MCP server that lets an AI assistant manage Docker containers, images, networks, volumes, Compose projects and registries through natural language.
- What you can do
- List, create, start, stop, restart, kill, pause, inspect and remove containers, and read logs and stats
- Pull, push, tag, build, inspect and remove images, including history and layers
- Create, inspect and remove networks and volumes, and connect or disconnect containers
- Run commands inside running containers and inspect exec instances
- Start, stop, restart, build and validate Docker Compose services, and view their logs and status
- Query system info and version, stream events, prune unused resources, and search or authenticate against Docker Hub and GHCR
- When to use it
- Useful when you want an assistant to inspect and operate a local or remote Docker environment: checking what is running, reading logs, running commands in containers, or bringing Compose stacks up and down without switching to a terminal.
- Requirements
- Runs locally over stdio via npx or a global npm install; needs Node.js 18 or higher and a running, accessible Docker daemon. Socket paths are auto-detected per platform; remote hosts use DOCKER_HOST, DOCKER_PORT, DOCKER_PROTOCOL, DOCKER_SOCKET_PATH, DOCKER_CERT_PATH and DOCKER_TLS_VERIFY, with network access and TLS certificates where applicable.
Installation
In SourceWeft
- Open Docker Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Docker MCP Server
Powerful Docker management for AI assistants
A comprehensive Model Context Protocol (MCP) server that empowers AI assistants like Cursor, Claude Desktop, and other MCP-compatible clients to seamlessly manage Docker containers, images, networks, volumes, and registries through natural language interactions.
Why Docker MCP Server?
- Zero Configuration - Works out of the box with
npx, no installation needed - Safety First - Two-step confirmation for destructive operations
- Cross-Platform - Works on Windows, Linux, and macOS with automatic Docker socket detection
- Comprehensive - Full Docker API coverage including Compose, registries, and system operations
- AI-Native - Designed specifically for AI assistants with clear, structured responses
[Features] Features
Container Management
- Full lifecycle control: Create, start, stop, restart, kill, and remove containers
- Monitoring: Real-time logs, statistics, and container inspection
- Advanced operations: Pause/unpause, exec commands, and resource management
Image Management
- Registry operations: Pull, push, tag, and remove images
- Build support: Build images from Dockerfiles with full configuration
- Inspection: Detailed image history, layers, and metadata
Network Management
- Network operations: Create, remove, and inspect Docker networks
- Container connectivity: Connect/disconnect containers from networks
- Network discovery: List and filter networks with advanced options
Volume Management
- Volume operations: Create, remove, and inspect volumes
- Data persistence: Manage persistent storage for containers
- Volume inspection: Detailed volume information and mount points
System Operations
- System information: Docker daemon info, version, and capabilities
- Resource cleanup: Prune unused images, containers, volumes, and networks
- Event monitoring: Real-time Docker event stream
Container Execution
- Command execution: Run commands in running containers
- Interactive sessions: Create and manage exec instances
- Output streaming: Real-time command output and logs
Registry Integration
- Docker Hub: Search repositories, list tags, authenticate, pull/push images
- GitHub Container Registry (GHCR): Full authentication and image management
- Multi-registry support: Seamlessly work with multiple registries
Docker Compose Support
- Multi-container management: Start, stop, restart compose services
- Service monitoring: View logs and status of compose services
- Build operations: Build compose services with dependency management
- Configuration validation: Parse and validate docker-compose.yml files
Safety Features
- Two-step confirmation for all destructive operations
- Resource preview: See what will be deleted before confirmation
- Dual confirmation methods:
- Confirm parameter (default): Works everywhere, simple and reliable
- MCP Elicitation API (advanced): Interactive form-based confirmation for better UX
[Installation] Installation
Via npx (Recommended)
Local Installation
Or install locally in your project:
[Quick Start] Quick Start
With Cursor
- Add to your Cursor MCP configuration (usually in
.cursor/mcp.jsonor similar):
- Restart Cursor and start managing Docker with AI!
With Claude Desktop
- Add to your Claude Desktop configuration:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- macOS:
- Restart Claude Desktop and start managing Docker with AI!
Local Development and Testing
Prerequisites
- Node.js 18.0.0 or higher
- Docker daemon running
- npm or yarn
Setup
- Clone the repository:
- Install dependencies:
- Build the project:
Running Locally
Method 1: Using npm start (after build)
Method 2: Using npm run dev (development mode with tsx)
This uses tsx to run TypeScript directly without building.
Method 3: Direct execution
Method 4: Using the binary
Development Workflow
- Make changes to source files in
src/ - Build the project:
- Test the changes:
- Check for TypeScript errors:
- Lint the code:
Troubleshooting
Docker connection issues:
- Ensure Docker daemon is running:
docker ps - Linux/macOS: Check Docker socket permissions:
ls -la /var/run/docker.sock - Windows: Ensure Docker Desktop is running and named pipe is accessible
- For remote Docker, set environment variables:
DOCKER_HOST,DOCKER_CERT_PATH, etc. - macOS: If
/var/run/docker.sockdoesn't exist, try~/.docker/run/docker.sock(Docker Desktop 4.0+)
Build errors:
- Clear node_modules and reinstall:
rm -rf node_modules && npm install - Check TypeScript version compatibility
- Ensure all dependencies are installed:
npm install
Runtime errors:
- Check that Docker is accessible:
docker version - Verify the build was successful:
ls -la dist/ - Check server logs (errors are written to stderr)
[Configuration] Configuration
The server automatically detects the operating system and uses the appropriate Docker socket path:
Platform-Specific Defaults
- Linux:
/var/run/docker.sock(Unix socket) - macOS:
/var/run/docker.sockor~/.docker/run/docker.sock(Docker Desktop 4.0+) - Windows:
//./pipe/docker_engine(Named pipe)
Connection Methods (in order of priority)
-
Environment variables (highest priority):
DOCKER_HOST- Docker daemon host (e.g.,tcp://localhost:2376,npipe:////./pipe/docker_engine)DOCKER_PORT- Docker daemon portDOCKER_PROTOCOL- Protocol (httporhttps)DOCKER_SOCKET_PATH- Path to Docker socket (overrides platform default)DOCKER_CERT_PATH- Path to Docker certificates directoryDOCKER_TLS_VERIFY- Enable TLS verification (1or0)
-
Platform-specific defaults (automatic detection):
- Linux:
/var/run/docker.sock - macOS:
/var/run/docker.sock(or~/.docker/run/docker.sockif available) - Windows:
//./pipe/docker_engine
- Linux:
Windows Configuration
On Windows, Docker Desktop uses named pipes. The server automatically detects Windows and uses the correct path. You can also explicitly set:
Remote Docker Host
To connect to a remote Docker host:
[Available Tools] Available Tools
Container Tools
docker_list_containers- List all containersdocker_create_container- Create a new containerdocker_start_container- Start a containerdocker_stop_container- Stop a containerdocker_restart_container- Restart a containerdocker_kill_container- Kill a containerdocker_remove_container- Remove a containerdocker_inspect_container- Get container detailsdocker_container_logs- Get container logsdocker_container_stats- Get container statisticsdocker_pause_container- Pause a containerdocker_unpause_container- Unpause a container
Image Tools
docker_list_images- List all imagesdocker_pull_image- Pull an image from registrydocker_push_image- Push an image to registrydocker_tag_image- Tag an imagedocker_remove_image- Remove an imagedocker_inspect_image- Get image detailsdocker_image_history- Get image history
Network Tools
docker_list_networks- List all networksdocker_create_network- Create a networkdocker_remove_network- Remove a networkdocker_inspect_network- Get network detailsdocker_connect_container- Connect container to networkdocker_disconnect_container- Disconnect container from network
Volume Tools
docker_list_volumes- List all volumesdocker_create_volume- Create a volumedocker_remove_volume- Remove a volumedocker_inspect_volume- Get volume details
System Tools
docker_system_info- Get Docker system informationdocker_version- Get Docker versiondocker_prune_system- Prune all unused resourcesdocker_prune_images- Prune unused imagesdocker_prune_containers- Prune stopped containersdocker_prune_volumes- Prune unused volumesdocker_prune_networks- Prune unused networks
Exec Tools
docker_exec- Execute a command in a containerdocker_inspect_exec- Get exec instance details
Compose Tools
docker_compose_up- Start Docker Compose servicesdocker_compose_down- Stop and remove Docker Compose servicesdocker_compose_ps- List Docker Compose servicesdocker_compose_logs- View output from Docker Compose servicesdocker_compose_config- Parse and validate docker-compose.yml filedocker_compose_build- Build Docker Compose servicesdocker_compose_restart- Restart Docker Compose servicesdocker_compose_stop- Stop Docker Compose servicesdocker_compose_start- Start Docker Compose services
Registry Tools
dockerhub_search- Search Docker Hubdockerhub_get_tags- Get repository tags from Docker Hubdockerhub_authenticate- Authenticate with Docker Hubdockerhub_pull- Pull from Docker Hubdockerhub_push- Push to Docker Hubghcr_authenticate- Authenticate with GitHub Container Registryghcr_pull- Pull from GHCRghcr_push- Push to GHCR
[Examples] Examples
List running containers
Create and start a container
Then start it:
Pull an image from Docker Hub
Search Docker Hub
Execute a command in a container
Start Docker Compose services
View Compose logs
Removing Resources with Confirmation
All destructive operations (remove, kill, prune) support two confirmation methods:
Method 1: Confirm Parameter (Default - Works Everywhere)
Step 1: Preview (without confirm)
This returns volume details and a warning message.
Step 2: Confirm (with confirm=true)
This actually removes the volume.
Method 2: MCP Elicitation API (Advanced - Better UX)
If your MCP client (Cursor, Claude Desktop) supports Elicitation API, you can use interactive confirmation:
This will show an interactive confirmation dialog in the client (if supported). The client will display a form asking for confirmation, and the operation proceeds only if the user accepts.
Note: Elicitation API support depends on the MCP client. If the client doesn't support it, the server automatically falls back to the confirm parameter method.
Operations requiring confirmation:
docker_remove_volume- Remove volumesdocker_remove_container- Remove containersdocker_kill_container- Kill containersdocker_remove_image- Remove imagesdocker_remove_network- Remove networksdocker_prune_system- Prune all unused resourcesdocker_prune_images- Prune unused imagesdocker_prune_containers- Prune stopped containersdocker_prune_volumes- Prune unused volumesdocker_prune_networks- Prune unused networks
Testing the Server
Quick Test
- Build the project:
- Use the test script:
Or test manually:
- Test Docker connection:
If Docker is running, you should see:
- Test with a simple MCP request (using jq for JSON formatting):
Note: The server communicates via stdio, so it will wait for JSON-RPC requests. Press Ctrl+C to exit.
Manual Testing Steps
- Start the server:
-
In another terminal, test with curl (if using HTTP transport) or use an MCP client
-
Verify Docker operations work:
- List containers: Use
docker_list_containerstool - Check system info: Use
docker_system_infotool
- List containers: Use
Integration Testing
For full integration testing, you'll need an MCP client. The server communicates via stdio (standard input/output), so it's designed to work with MCP-compatible clients like:
- Cursor IDE
- Claude Desktop
- Custom MCP clients
Debugging
Enable verbose logging by checking stderr output. The server writes errors and status messages to stderr:
[Requirements] Requirements
- Node.js 18.0.0 or higher
- Docker daemon running and accessible
- Supported Platforms:
- Linux (x64, ARM64)
- macOS (Intel, Apple Silicon)
- Windows (x64, ARM64)
- For remote Docker: Proper network access and TLS certificates (if using TLS)
Platform-Specific Notes
- Linux: Requires Docker daemon with Unix socket at
/var/run/docker.sock - macOS: Works with Docker Desktop. Automatically detects socket location.
- Windows: Works with Docker Desktop. Uses named pipe
//./pipe/docker_engine
Quick Start (Local Development)
License
MIT
Testing with MCP Clients
Testing with Cursor (Local Development)
If you're developing locally and want to test with Cursor:
- Build the project:
- Add to Cursor MCP configuration (usually in
.cursor/mcp.jsonor similar):
Or if using the binary:
Testing with Claude Desktop (Local Development)
If you're developing locally and want to test with Claude Desktop:
- Build the project:
- Add to Claude Desktop configuration:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- macOS:
Testing with MCP Inspector (CLI)
You can test the server using MCP Inspector or any MCP client:
[Contributing] Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Source: README.md at commit b4f9de5
Tools
0Version history
1- v0.2.4LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.
Other Docker integrations
Docker Recipes
recipes.dockerOfficial publisher
A remote MCP server that lets an assistant search and fetch ready-to-run Docker Compose stacks for self-hosting and home labs.

XenMCP Docker agent
com.xenmcp
Read-only MCP server for one Docker host: lets an assistant list and inspect containers, read logs, view live stats and recent events, with no exec or changes.

Reverse Engineer Anything (Docker)
Published by GitHub account psyb0t
A Docker-packaged REA reverse-engineering server that lets an assistant decompile APKs, inspect binaries and drive Android devices over adb.

Docker Hub Mcp
Published by GitHub account mrfentmen
Looks up Docker Hub images, their tags and pull counts, so an assistant can check container images without an API key.

Docker Image Shape
Published by GitHub account sadri-dridi
Remote MCP server of small, mostly stateless utility checks: Docker image name shape, URL and hostname parsing, HTTP status probes, time, and arithmetic.