What is MCP_DOCKER?
MCP_DOCKER is a Docker-based platform that enables developers to create agentic AI workflows using Markdown and various tools, allowing for complex interactions with language models.
How to use MCP_DOCKER?
To use MCP_DOCKER, install the VSCode extension or run commands in the terminal to set up your environment, register prompts, and execute workflows with your chosen language model.
Key features of MCP_DOCKER?
- Integration of Dockerized tools for enhanced functionality
- Support for multi-model agents to optimize task execution
- Ability to write and run workflows in Markdown format
- Project context extraction for tailored assistance
Use cases of MCP_DOCKER?
- Automating software development workflows
- Running complex AI-driven tasks in a controlled environment
- Creating and managing prompts for various AI models
FAQ from MCP_DOCKER?
- Can MCP_DOCKER work with any language model?
Yes! MCP_DOCKER is designed to be compatible with various LLMs, allowing flexibility in your workflows.
- Is there a graphical interface for MCP_DOCKER?
While the primary interaction is through Markdown and command line, the VSCode extension provides a user-friendly interface.
- How do I get started with MCP_DOCKER?
You can start by installing the VSCode extension and following the setup instructions provided in the documentation.
This README is an agentic workflow
AI Tools for Developers
Agentic AI workflows enabled by Docker containers.
Just Docker. Just Markdown. BYOLLM.
MCP
Any prompts you write and their tools can now be used as MCP servers
Use serve mode with --mcp flag. Then, register prompts via git ref or path with --register <ref>
# ...
serve
--mcp
--register github:docker/labs-ai-tools-for-devs?path=prompts/examples/generate_dockerfile.md
--register /Users/ai-overlordz/some/local/prompt.md
# ...
Source for many experiments in our LinkedIn newsletter
What is this?
This is a simple Docker image which enables infinite possibilities for novel workflows by combining Dockerized Tools, Markdown, and the LLM of your choice.
Markdown is the language
Humans already speak it. So do LLM's. This software allows you to write complex workflows in a markdown files, and then run them with your own LLM in your editor or terminal...or any environment, thanks to Docker.
Dockerized Tools
OpenAI API compatiable LLM's already support tool calling. We believe these tools could just be Docker images. Some of the benefits using Docker based on our research are enabling the LLM to:
- take more complex actions
- get more context with fewer tokens
- work across a wider range of environments
- operate in a sandboxed environment
Conversation Loop
The conversation loop is the core of each workflow. Tool results, agent responses, and of course, the markdown prompts, are all passed through the loop. If an agent sees an error, it will try running the tool with different parameters, or even different tools until it gets the right result.
Multi-Model Agents
Each prompt can be configured to be run with different LLM models, or even different model families. This allows you to use the best tool for the job. When you combine these tools, you can create multi-agent workflows where each agent runs with the model best suited for that task.
With Docker, it is possible to have frontier models plan, while lightweight local models execute.
Project-First Design
To get help from an assistant in your software development loop, the only context necessary is the project you are working on.
Extracting project context
An extractor is a Docker image that runs against a project and extracts information into a JSON context.
Prompts as a trackable artifact
Prompts are stored in a git repo and can be versioned, tracked, and shared for anyone to run in their own environment.
Get Started
We highly recommend using the VSCode extension to get started. It will help you create prompts, and run them with your own LLM.
Running your first loop
VSCode
Install Extension
Get the latest release and install with
code --install-extension 'labs-ai-tools-vscode-<version>.vsix'
Running:
- Open an existing markdown file, or create a new markdown file in VSCode.
You can even run this markdown file directly!
-
Run command
>Docker AI: Set OpenAI API Keyto set an OpenAI API key, or use a dummy value for local models. -
Run command
>Docker AI: Select target projectto select a project to run the prompt against. -
Run command
>Docker AI: Run Promptto start the conversation loop.
CLI
Instructions assume you have a terminal open, and Docker Desktop running.
- Set OpenAI key
echo $OPENAI_API_KEY > $HOME/.openai-api-key
Note: we assume this file exists, so you must set a dummy value for local models.
- Run the container in your project directory
docker run
--rm \
--pull=always \
-it \
-v /var/run/docker.sock:/var/run/docker.sock \
--mount type=volume,source=docker-prompts,target=/prompts \
--mount type=bind,source=$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 for more details on how to run the conversation loop.
Building
#docker:command=build
docker build -t vonwig/prompts:local -f Dockerfile .
Now, for the agentic workflow...
prompt system
You are an expert at reading readmes.
Use curl to get the readme for https://github.com/docker/labs-ai-tools-for-devs before answering the following questions.
prompt user
What is this project?
