Skip to main content
Glama
Krelborn

docker-compose-mcp

by Krelborn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Docker Compose MCP Server

An MCP (Model Context Protocol) server that enables Claude to manage Docker Compose containers on your local machine.

Features

  • Update containers: Stop, pull latest images, and restart containers in one command

  • Run any docker compose command: Execute arbitrary docker compose commands

  • Safe error handling: Graceful error handling with detailed feedback

Related MCP server: Docker MCP

Installation

  1. Install dependencies:

npm install

  1. Build the TypeScript code:

npm run build

Configuration for Claude Desktop

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "docker-compose": {
      "command": "node",
      "args": [
        "/absolute/path/to/docker-compose-mcp-server/dist/index.js"
      ]
    }
  }
}

Replace /absolute/path/to/docker-compose-mcp-server with the actual path where you saved this project.

Usage Examples

Once configured, you can interact with Docker Compose through Claude:

Update containers

"Update my chemdraw containers at /Users/matt/Documents/chemdraw-js/chemdraw-js-compose.yml"

View container status

"Show me the status of my docker containers in /Users/matt/Documents/chemdraw-js/chemdraw-js-compose.yml"

View logs

"Show me the logs from my docker containers"

Restart containers

"Restart the containers in my compose file"

Available Tools

docker_compose_update

Updates Docker Compose containers by:

  1. Stopping running containers (docker compose down)

  2. Pulling latest images (docker compose pull)

  3. Starting containers (docker compose up -d)

Parameters:

  • compose_file (string, required): Absolute path to the docker-compose.yml file

  • detached (boolean, optional): Run in detached mode (default: true)

docker_compose_command

Execute any docker compose command.

Parameters:

  • compose_file (string, required): Absolute path to the docker-compose.yml file

  • command (string, required): Docker compose command to run (e.g., "ps", "logs", "restart")

Security Considerations

This MCP server executes docker commands with the permissions of the user running Claude Desktop. Ensure you:

  • Only use trusted compose files

  • Understand the commands being executed

  • Review Claude's suggested commands before confirming destructive operations

Development

Watch mode for development:

npm run dev

Troubleshooting

"docker: not found"

Make sure Docker is installed and in your PATH. Test by running docker --version in your terminal.

"Permission denied"

Ensure your user has permission to run Docker commands. On Linux, you may need to add your user to the docker group.

"Cannot find module"

Make sure you've run npm run build before starting the server.

License

MIT

Available Tools

2 tools
docker_compose_commandRun Docker Compose CommandA

Execute any docker compose command for a specific compose file.

This tool allows running arbitrary docker compose commands like:

  • ps: List containers

  • logs: View container logs

  • restart: Restart services

  • stop/start: Stop or start services

  • exec: Execute commands in running containers

Args:

  • compose_file (string): Absolute path to the docker-compose.yml file

  • command (string): Docker compose command to run (everything after 'docker compose -f file.yml')

Returns: The stdout and stderr output from the docker compose command

Examples:

  • Use when: "Show me the logs for my docker containers"

  • Use when: "List running docker compose services"

  • Use when: "Restart the web service"

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesDocker compose command to run (e.g., 'ps', 'logs', 'restart')
compose_fileYesAbsolute path to the docker-compose.yml file

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations already declaring readOnly=false, destructive=false, openWorld=false and idempotent=false, the description usefully adds that the command is arbitrary passthrough and that stdout/stderr are returned. It does not address permissions, side-effect risk, or that some listed commands (stop/start/restart/exec) mutate running state, which is worth flagging given destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded opening sentence states the operation immediately, and the bulleted subcommand list plus examples are scannable. The 'Args/Returns/Examples' scaffolding is slightly heavier than needed for a two-parameter tool, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by explaining that stdout and stderr are returned. Inputs, return shape, and usage scenarios are all covered; the only meaningful gap is the absence of any note about interaction with the sibling update tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The Args section restates both parameters, and only the clarification that 'command' is everything after 'docker compose -f file.yml' genuinely adds meaning beyond the schema's own descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Execute any docker compose command for a specific compose file') and even enumerates supported subcommands, so the purpose is unmistakable. It stops short of distinguishing itself from the sibling docker_compose_update, leaving the agent to infer that mutation-by-update goes elsewhere.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Three concrete 'Use when' examples anchor real scenarios (view logs, list services, restart a service), which is solid contextual guidance. However, there are no exclusions and no routing to docker_compose_update, so the agent gets positive signals but no disambiguation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

docker_compose_updateUpdate Docker Compose ContainersA
Destructive

Update Docker Compose containers by stopping them, pulling latest images, and restarting.

This tool executes the standard update workflow:

  1. Stop running containers (docker compose down)

  2. Pull latest images (docker compose pull)

  3. Start containers with new images (docker compose up -d)

Args:

  • compose_file (string): Absolute path to the docker-compose.yml file

  • detached (boolean): Run containers in detached mode (default: true)

Returns: A summary of each step's output, including:

  • Which containers were stopped

  • Which images were pulled/updated

  • Which containers are now running

  • Any errors encountered during the process

Examples:

  • Use when: "Update my chemdraw containers"

  • Use when: "Pull latest images and restart docker compose"

Error Handling:

  • If 'down' fails, continues to 'pull' (containers may not be running)

  • If 'pull' fails, does not proceed to 'up'

  • If 'up' fails, reports error details

ParametersJSON Schema
NameRequiredDescriptionDefault
detachedNoRun containers in detached mode (default: true)
compose_fileYesAbsolute path to the docker-compose.yml file

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false. The description greatly enhances this by detailing the exact destructive steps (stopping, pulling, restarting), the order of operations, and robust error handling logic (continuing after 'down' failure, stopping after 'pull' failure). It also specifies the return summary contents, adding significant value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (workflow, args, returns, examples, error handling). It is slightly verbose, especially in repeating argument descriptions that are already in the schema, but the front-loaded purpose and numbered steps aid quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multi-step destructive operation), lack of output schema, and the need for clear error handling, the description is complete. It covers the workflow, arguments, return summary, usage examples, and error behavior, leaving no critical gaps for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with parameter descriptions already present. The description adds minor value by listing the arguments and their defaults/purposes, but doesn't introduce new syntax or constraints beyond what is in the schema. Given the high schema coverage, a score of 4 is appropriate as it provides a clear consolidated view without being redundant.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Update Docker Compose containers') and details the exact three-step workflow (down, pull, up -d). It distinguishes itself from the sibling docker_compose_command by being a high-level orchestrated update rather than a generic command executor.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides concrete 'Use when' examples for update scenarios, clearly implying this tool is for updating containers. However, it doesn't explicitly state when to use the sibling docker_compose_command instead, nor does it state any exclusions (e.g., not for initial deployment).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observeddocker_compose_command
    • First observeddocker_compose_update
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored across 2 tools

Disambiguation4/5

docker_compose_update is a specialized workflow while docker_compose_command is a general executor. They overlap because the update workflow can also be run via the generic command, but the distinction is clear enough for an agent to choose correctly.

Naming Consistency4/5

Both tools use snake_case with a consistent docker_compose_ prefix. The only minor inconsistency is that 'update' is a verb while 'command' is a noun, but the pattern is still predictable and readable.

Tool Count3/5

Two tools is borderline thin for a server. While the generic command covers many operations, the specialized update tool means each tool earns its place, but more structured tools for common operations could improve usability.

Completeness5/5

The generic docker_compose_command can execute any docker compose command, covering the full lifecycle (up, down, logs, ps, exec, etc.). The update tool handles a common workflow, so there are no obvious gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers