# labs-ai-tools-for-devs

> MCP Server

This repository provides a Docker image enabling agentic AI workflows using Dockerized tools, Markdown prompts, and your own LLM for complex tasks and MCP servers. It allows you to create

## Overview

- **Category:** Developer Tools
- **Language:** HTML
- **Stars:** 392
- **Forks:** 32
- **Owner:** docker
- **GitHub:** https://github.com/docker/labs-ai-tools-for-devs
- **Homepage:** https://www.linkedin.com/newsletters/docker-labs-genai-7204877599427194882/
- **Created:** 2024-07-10T04:14:12+00:00
- **Updated:** 2025-03-28T16:29:17+00:00
- **Source:** https://model-context-protocol.com/servers/docker-ai-agent-prompt-runner-server

## Setup

## Setup

### VSCode

**Install Extension**

Get the [latest release](https://github.com/docker/labs-ai-tools-vscode/releases/latest) and install with

```sh 
code --install-extension 'labs-ai-tools-vscode-<version>.vsix'
```

**Running:**

1. Open an existing markdown file, or create a new markdown file in VSCode.
> You can even run *this* markdown file directly!

2. Run command `>Docker AI: Set OpenAI API Key` to set an OpenAI API key, or use a dummy value for local models.

3. Run command `>Docker AI: Select target project` to select a project to run the prompt against.

4. Run command `>Docker AI: Run Prompt` to start the conversation loop.

### CLI

Instructions assume you have a terminal open, and Docker Desktop running.

1. Set OpenAI key
```sh
echo $OPENAI_API_KEY > $HOME/.openai-api-key
```
Note: we assume this file exists, so you must set a dummy value for local models.

2. Run the container in your project directory

```sh
docker run 
  --rm \
  --pull=always \
  -it \
  -v /var/run/docker.sock:/var/run/docker.sock \
  --mount type=volume,source=docker-prompts,target=/prompts \
  --mount type=bind,source=$HOME/.openai-api-key,target=/root/.openai-api-key \
  vonwig/prompts:latest \
    run \
    --host-dir $PWD \
    --user $USER \
    --platform "$(uname -o)" \
    --prompts "github:docker/labs-githooks?ref=main&path=prompts/git_hooks"
```

See [docs](https://vonwig.github.io/prompts.docs/#/page/running%20the%20prompt%20engine) for more details on how to run the conversation loop.

## Tools

## Available Tools

1.  **MCP Servers**: Prompts and tools can be used as MCP servers.
2.  **VSCode Extension**: A VSCode extension is available to help create and run prompts.
3.  **Dockerized Tools**: Allows LLMs to take complex actions, get more context, work across environments, and operate in a sandboxed environment.
4.  **Conversation Loop**: Tool results, agent responses, and markdown prompts are passed through the loop.
5.  **Multi-Model Agents**: Prompts can be configured to run with different LLM models or families.
6.  **Project-First Design**: Context is extracted from the project to assist in the software development loop.
7.  **Prompts as a trackable artifact**: Prompts are stored in a git repo and can be versioned, tracked, and shared.