AI Tools for Developers MCP Server

@docker

Repository Homepage

Basic information

About AI Tools for Developers MCP Server

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

#mathgpt #math-solver #math-assistant

AI Tools for Developers MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

AI Tools for Developers MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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

Frequently asked questions

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`.

Comments

More Other MCP servers

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K