MCP.so
登录

AI Tools for Developers

@docker

关于 AI Tools for Developers

Your trusted home for discovering MCP tools – seamlessly integrated into Docker

基本信息

分类

其他

许可证

Apache-2.0

运行时

clojure

传输方式

stdio

发布者

docker

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "MCP_DOCKER": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "alpine/socat",
        "STDIO",
        "TCP:host.docker.internal:8811"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is AI Tools for Developers?

AI Tools for Developers is a deprecated Docker‑based system that enables agentic AI workflows by combining Dockerized tools, Markdown prompts, and an LLM of your choice. It allowed developers to write complex workflows in Markdown and run them in their editor, terminal, or any environment via Docker. The repository is now replaced by the integrated MCP Toolkit in Docker Desktop.

How to use AI Tools for Developers?

Install the VSCode extension or use the CLI docker run command. For MCP serve mode, pass the --mcp flag and register prompts using --register <git ref or path>. Set an OpenAI API key (or a dummy value for local models), then run the conversation loop in your editor or terminal.

Key features of AI Tools for Developers

  • Dockerized tools for sandboxed execution
  • Markdown as the workflow language
  • Conversation loop with automatic error correction
  • Multi‑model agents using different LLMs
  • Project‑first design with context extraction
  • MCP server support with prompt registration

Use cases of AI Tools for Developers

  • Automating software development tasks with AI assistants
  • Creating multi‑agent workflows that combine frontier and local models
  • Running repeatable, version‑controlled prompts across projects
  • Extracting structured context from source code repositories
  • Experimenting with agentic workflows in VSCode or the CLI

FAQ from AI Tools for Developers

Is AI Tools for Developers still maintained?

No. This repository is deprecated and no longer under active development. Please use the integrated MCP Toolkit in Docker Desktop instead.

How do I start the MCP server?

Launch the tool with the serve subcommand and the --mcp flag. Then register prompts using --register github:<ref> or --register /local/path.

What runtime environment is required?

Docker Desktop must be running. An OpenAI API key (or a dummy value for local models) is required. For CLI use, mount the Docker socket and the API key file as shown in the README.

Can I use local LLMs with AI Tools for Developers?

Yes. The system supports multiple models; you can use a dummy API key for local models and configure each prompt to run with a different model family.

How do I run prompts in VSCode?

Install the VSCode extension, set an OpenAI API key via the >Docker AI: Set OpenAI API Key command, select a target project, and run >Docker AI: Run Prompt.

评论

其他 分类下的更多 MCP 服务器