{"type":"mcp_server","name":"labs-ai-tools-for-devs","description":"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","category":"Developer Tools","language":"HTML","stars":386,"forks":32,"owner":"docker","github_url":"https://github.com/docker/labs-ai-tools-for-devs","homepage":"https://www.linkedin.com/newsletters/docker-labs-genai-7204877599427194882/","setup":"## Setup\n\n### VSCode\n\n**Install Extension**\n\nGet the [latest release](https://github.com/docker/labs-ai-tools-vscode/releases/latest) and install with\n\n```sh \ncode --install-extension 'labs-ai-tools-vscode-<version>.vsix'\n```\n\n**Running:**\n\n1. Open an existing markdown file, or create a new markdown file in VSCode.\n> You can even run *this* markdown file directly!\n\n2. Run command `>Docker AI: Set OpenAI API Key` to set an OpenAI API key, or use a dummy value for local models.\n\n3. Run command `>Docker AI: Select target project` to select a project to run the prompt against.\n\n4. Run command `>Docker AI: Run Prompt` to start the conversation loop.\n\n### CLI\n\nInstructions assume you have a terminal open, and Docker Desktop running.\n\n1. Set OpenAI key\n```sh\necho $OPENAI_API_KEY > $HOME/.openai-api-key\n```\nNote: we assume this file exists, so you must set a dummy value for local models.\n\n2. Run the container in your project directory\n\n```sh\ndocker run \n  --rm \\\n  --pull=always \\\n  -it \\\n  -v /var/run/docker.sock:/var/run/docker.sock \\\n  --mount type=volume,source=docker-prompts,target=/prompts \\\n  --mount type=bind,source=$HOME/.openai-api-key,target=/root/.openai-api-key \\\n  vonwig/prompts:latest \\\n    run \\\n    --host-dir $PWD \\\n    --user $USER \\\n    --platform \"$(uname -o)\" \\\n    --prompts \"github:docker/labs-githooks?ref=main&path=prompts/git_hooks\"\n```\n\nSee [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\n\n1.  **MCP Servers**: Prompts and tools can be used as MCP servers.\n2.  **VSCode Extension**: A VSCode extension is available to help create and run prompts.\n3.  **Dockerized Tools**: Allows LLMs to take complex actions, get more context, work across environments, and operate in a sandboxed environment.\n4.  **Conversation Loop**: Tool results, agent responses, and markdown prompts are passed through the loop.\n5.  **Multi-Model Agents**: Prompts can be configured to run with different LLM models or families.\n6.  **Project-First Design**: Context is extracted from the project to assist in the software development loop.\n7.  **Prompts as a trackable artifact**: Prompts are stored in a git repo and can be versioned, tracked, and shared.","faq":null,"created_at":"2024-07-10T04:14:12+00:00","updated_at":"2025-03-28T16:29:17+00:00","source_url":"https://model-context-protocol.com/servers/docker-ai-agent-prompt-runner-server","related_articles":[]}