mcp-server-docker

Name: mcp-server-docker
Author: ckreiling

733stars97forks

How to install mcp-server-docker?

ckreiling/mcp-server-docker

$git clone https://github.com/ckreiling/mcp-server-docker

Installs into the current project.

Summary

An MCP server for managing Docker with natural language!

Files · 1

View on GitHub

README.md

1	# 🐋 Docker MCP server
2
3	An MCP server for managing Docker with natural language!
4
5	## 🪩 What can it do?
6
7	- 🚀 Compose containers with natural language
8	- 🔍 Introspect & debug running containers
9	- 📀 Manage persistent data with Docker volumes
10
11	## ❓ Who is this for?
12
13	- Server administrators: connect to remote Docker engines for e.g. managing a
14	public-facing website.
15	- Tinkerers: run containers locally and experiment with open-source apps
16	supporting Docker.
17	- AI enthusiasts: push the limits of that an LLM is capable of!
18
19	## Demo
20
21	A quick demo showing a WordPress deployment using natural language:
22
23	https://github.com/user-attachments/assets/65e35e67-bce0-4449-af7e-9f4dd773b4b3
24
25	## 🏎️ Quickstart
26
27	### Install
28
29	#### Claude Desktop
30
31	On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
32
33	On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
34
35	<details>
36	<summary>Install from PyPi with uv</summary>
37
38	If you don't have `uv` installed, follow the installation instructions for your
39	system:
40	[link](https://docs.astral.sh/uv/getting-started/installation/#installation-methods)
41
42	Then add the following to your MCP servers file:
43
44	```
45	"mcpServers": {
46	"mcp-server-docker": {
47	"command": "uvx",
48	"args": [
49	"mcp-server-docker"
50	]
51	}
52	}
53	```
54
55	</details>
56
57	<details>
58	<summary>Install with Docker</summary>
59
60	Purely for convenience, the server can run in a Docker container.
61
62	After cloning this repository, build the Docker image:
63
64	```bash
65	docker build -t mcp-server-docker .
66	```
67
68	And then add the following to your MCP servers file:
69
70	```
71	"mcpServers": {
72	"mcp-server-docker": {
73	"command": "docker",
74	"args": [
75	"run",
76	"-i",
77	"--rm",
78	"-v",
79	"/var/run/docker.sock:/var/run/docker.sock",
80	"mcp-server-docker:latest"
81	]
82	}
83	}
84	```
85
86	Note that we mount the Docker socket as a volume; this ensures the MCP server
87	can connect to and control the local Docker daemon.
88
89	</details>
90
91	## 📝 Prompts
92
93	### 🎻 `docker_compose`
94
95	Use natural language to compose containers. [See above](#demo) for a demo.
96
97	Provide a Project Name, and a description of desired containers, and let the LLM
98	do the rest.
99
100	This prompt instructs the LLM to enter a `plan+apply` loop. Your interaction
101	with the LLM will involve the following steps:
102
103	1. You give the LLM instructions for which containers to bring up
104	2. The LLM calculates a concise natural language plan and presents it to you
105	3. You either:
106	- Apply the plan
107	- Provide the LLM feedback, and the LLM recalculates the plan
108
109	#### Examples
110
111	- name: `nginx`, containers: "deploy an nginx container exposing it on port
112	9000"
113	- name: `wordpress`, containers: "deploy a WordPress container and a supporting
114	MySQL container, exposing Wordpress on port 9000"
115
116	#### Resuming a Project
117
118	When starting a new chat with this prompt, the LLM will receive the status of
119	any containers, volumes, and networks created with the given project `name`.
120
121	This is mainly useful for cleaning up, in-case you lose a chat that was
122	responsible for many containers.
123
124	## 📔 Resources
125
126	The server implements a couple resources for every container:
127
128	- Stats: CPU, memory, etc. for a container
129	- Logs: tail some logs from a container
130
131	## 🔨 Tools
132
133	### Containers
134
135	- `list_containers`
136	- `create_container`
137	- `run_container`
138	- `recreate_container`
139	- `start_container`
140	- `fetch_container_logs`
141	- `stop_container`
142	- `remove_container`
143
144	### Images
145
146	- `list_images`
147	- `pull_image`
148	- `push_image`
149	- `build_image`
150	- `remove_image`
151
152	### Networks
153
154	- `list_networks`
155	- `create_network`
156	- `remove_network`
157
158	### Volumes
159
160	- `list_volumes`
161	- `create_volume`
162	- `remove_volume`
163
164	## 🚧 Disclaimers
165
166	### Sensitive Data
167
168	DO NOT CONFIGURE CONTAINERS WITH SENSITIVE DATA. This includes API keys,
169	database passwords, etc.
170
171	Any sensitive data exchanged with the LLM is inherently compromised, unless the
172	LLM is running on your local machine.
173
174	If you are interested in securely passing secrets to containers, file an issue
175	on this repository

People who liked this also viewed

6 picks

Type

mcp-proxy-for-awsAWS MCP Proxy ServerMCP ServersJul 20262.0M327
pydantic-ai-backendFile Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.MCP ServersJul 2026197k114
mcp-for-argocdAn implementation of Model Context Protocol (MCP) server for Argo CD.MCP ServersJul 202690k541
heroku-mcp-serverHeroku Platform MCP Server using the Heroku CLIMCP ServersJul 202626k80
ghost-mcpA Model Context Protocol (MCP) server for interacting with Ghost CMS through LLM interfaces like Claude. Allow you to control your Ghost blog by simply asking Claude etc.MCP ServersApr 202620k215
Google DriveUpload, organize, and share files in the cloud. Manage folders, set permissions, and search across stored documents.MCP Serversrecently15k0

mcp-server-docker

733stars97forks

View on GitHub

How to install mcp-server-docker?

ckreiling/mcp-server-docker

$git clone https://github.com/ckreiling/mcp-server-docker

Installs into the current project.

Summary

An MCP server for managing Docker with natural language!

Files · 1

View on GitHub

README.md

1	# 🐋 Docker MCP server
2
3	An MCP server for managing Docker with natural language!
4
5	## 🪩 What can it do?
6
7	- 🚀 Compose containers with natural language
8	- 🔍 Introspect & debug running containers
9	- 📀 Manage persistent data with Docker volumes
10
11	## ❓ Who is this for?
12
13	- Server administrators: connect to remote Docker engines for e.g. managing a
14	public-facing website.
15	- Tinkerers: run containers locally and experiment with open-source apps
16	supporting Docker.
17	- AI enthusiasts: push the limits of that an LLM is capable of!
18
19	## Demo
20
21	A quick demo showing a WordPress deployment using natural language:
22
23	https://github.com/user-attachments/assets/65e35e67-bce0-4449-af7e-9f4dd773b4b3
24
25	## 🏎️ Quickstart
26
27	### Install
28
29	#### Claude Desktop
30
31	On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
32
33	On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
34
35	<details>
36	<summary>Install from PyPi with uv</summary>
37
38	If you don't have `uv` installed, follow the installation instructions for your
39	system:
40	[link](https://docs.astral.sh/uv/getting-started/installation/#installation-methods)
41
42	Then add the following to your MCP servers file:
43
44	```
45	"mcpServers": {
46	"mcp-server-docker": {
47	"command": "uvx",
48	"args": [
49	"mcp-server-docker"
50	]
51	}
52	}
53	```
54
55	</details>
56
57	<details>
58	<summary>Install with Docker</summary>
59
60	Purely for convenience, the server can run in a Docker container.
61
62	After cloning this repository, build the Docker image:
63
64	```bash
65	docker build -t mcp-server-docker .
66	```
67
68	And then add the following to your MCP servers file:
69
70	```
71	"mcpServers": {
72	"mcp-server-docker": {
73	"command": "docker",
74	"args": [
75	"run",
76	"-i",
77	"--rm",
78	"-v",
79	"/var/run/docker.sock:/var/run/docker.sock",
80	"mcp-server-docker:latest"
81	]
82	}
83	}
84	```
85
86	Note that we mount the Docker socket as a volume; this ensures the MCP server
87	can connect to and control the local Docker daemon.
88
89	</details>
90
91	## 📝 Prompts
92
93	### 🎻 `docker_compose`
94
95	Use natural language to compose containers. [See above](#demo) for a demo.
96
97	Provide a Project Name, and a description of desired containers, and let the LLM
98	do the rest.
99
100	This prompt instructs the LLM to enter a `plan+apply` loop. Your interaction
101	with the LLM will involve the following steps:
102
103	1. You give the LLM instructions for which containers to bring up
104	2. The LLM calculates a concise natural language plan and presents it to you
105	3. You either:
106	- Apply the plan
107	- Provide the LLM feedback, and the LLM recalculates the plan
108
109	#### Examples
110
111	- name: `nginx`, containers: "deploy an nginx container exposing it on port
112	9000"
113	- name: `wordpress`, containers: "deploy a WordPress container and a supporting
114	MySQL container, exposing Wordpress on port 9000"
115
116	#### Resuming a Project
117
118	When starting a new chat with this prompt, the LLM will receive the status of
119	any containers, volumes, and networks created with the given project `name`.
120
121	This is mainly useful for cleaning up, in-case you lose a chat that was
122	responsible for many containers.
123
124	## 📔 Resources
125
126	The server implements a couple resources for every container:
127
128	- Stats: CPU, memory, etc. for a container
129	- Logs: tail some logs from a container
130
131	## 🔨 Tools
132
133	### Containers
134
135	- `list_containers`
136	- `create_container`
137	- `run_container`
138	- `recreate_container`
139	- `start_container`
140	- `fetch_container_logs`
141	- `stop_container`
142	- `remove_container`
143
144	### Images
145
146	- `list_images`
147	- `pull_image`
148	- `push_image`
149	- `build_image`
150	- `remove_image`
151
152	### Networks
153
154	- `list_networks`
155	- `create_network`
156	- `remove_network`
157
158	### Volumes
159
160	- `list_volumes`
161	- `create_volume`
162	- `remove_volume`
163
164	## 🚧 Disclaimers
165
166	### Sensitive Data
167
168	DO NOT CONFIGURE CONTAINERS WITH SENSITIVE DATA. This includes API keys,
169	database passwords, etc.
170
171	Any sensitive data exchanged with the LLM is inherently compromised, unless the
172	LLM is running on your local machine.
173
174	If you are interested in securely passing secrets to containers, file an issue
175	on this repository

People who liked this also viewed

6 picks

Type