MCPgee
MCPgee
MCPgeeMCPgee

Atlantis

v1.0.0•Developer Tools•stable

MCP-compatible dynamic function manager; can be used with our Greenland terrain server or standalone

atlantismcpai-integration
Share:
8
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Atlantis?

Atlantis is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp-compatible dynamic function manager; can be used with our greenland terrain server or standalone

MCP-compatible dynamic function manager; can be used with our Greenland terrain server or standalone

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP-compatible dynamic function manager; can be used with ou

Use Cases

Manage dynamic functions through MCP for terrain and landscape generation.
ProjectAtlantis-dev

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx atlantis

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Atlantis

Atlantis MCP Server is a dynamic function manager that connects AI assistants to the Project Atlantis platform, enabling terrain generation, home automation, and extensible tool discovery via MCP. It runs a Python backend that exposes tools dynamically based on app folders, and a lightweight Node.js MCP bridge that Claude or Codex connects to over a local port.

Prerequisites

  • Python 3.13 or later (async support required)
  • Node.js 18+ and npm installed
  • uv / uvx package manager installed
  • A Project Atlantis account (email + API key)
  • OpenRouter API key or Anthropic API key (depending on model backend)
1

Clone the repository

Clone the Atlantis MCP server repository from GitHub and navigate into the Python server directory.

git clone https://github.com/ProjectAtlantis-dev/atlantis-mcp-server.git
cd atlantis-mcp-server/python-server
2

Create a virtual environment and install dependencies

Set up an isolated Python environment and install all required packages from the requirements file.

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
3

Start the Python backend server

Launch the Atlantis Python server with your credentials. Replace the email, API key values, and service name with your own. The server connects to the Atlantis cloud and exposes tools locally on port 8000.

python server.py \
  [email protected] \
  --api-key=YOUR_API_KEY \
  --host=localhost \
  --port=8000 \
  --cloud-host=wss://projectatlantis.ai \
  --cloud-port=443 \
  --service-name=home
4

Register the MCP server with Claude Code

With the Python backend running, add the Atlantis MCP bridge to Claude Code using the atlantis-mcp npm package. This connects Claude to the local server on port 8000.

claude mcp add atlantis -- npx atlantis-mcp --port 8000
5

Configure Claude Desktop (alternative)

If using Claude Desktop instead of Claude Code, add the following block to your claude_desktop_config.json file to register the server.

{
  "mcpServers": {
    "atlantis": {
      "command": "npx",
      "args": ["atlantis-mcp", "--port", "8000"]
    }
  }
}
6

Verify dynamic tool discovery

Tools are loaded from the dynamic_functions/ directory, organized into app folders (e.g., Home, Accounting). Add new function files there and restart the server to expose them as MCP tools automatically.

ls dynamic_functions/

Atlantis Examples

Client configuration

Claude Desktop configuration connecting to the local Atlantis MCP bridge.

{
  "mcpServers": {
    "atlantis": {
      "command": "npx",
      "args": ["atlantis-mcp", "--port", "8000"]
    }
  }
}

Prompts to try

Example prompts that exercise Atlantis dynamic tools from within Claude.

- "Call the readme tool to show me what functions are available"
- "Use the Chat app to send_message to my home assistant"
- "Run the Home**status tool to check sensor states"
- "List all available dynamic functions in the Accounting app"

Troubleshooting Atlantis

Server exits immediately with an authentication error

Ensure --email and --api-key match your Project Atlantis account. The default api-key 'foobar' is only for local testing without cloud connection. Use the `api` command inside the server to update the key.

npx atlantis-mcp reports 'port refused connection'

The Python backend must be running before you connect the MCP bridge. Start server.py first, confirm it prints 'Listening on localhost:8000', then run the npx command.

Dynamic tools do not appear after adding a new function file

Tool discovery happens at startup. Restart the Python server after adding files to dynamic_functions/ so the new tools are registered with the MCP bridge.

Frequently Asked Questions about Atlantis

What is Atlantis?

Atlantis is a Model Context Protocol (MCP) server that mcp-compatible dynamic function manager; can be used with our greenland terrain server or standalone It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Atlantis?

Follow the installation instructions on the Atlantis GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Atlantis?

Atlantis works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Atlantis free to use?

Yes, Atlantis is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Atlantis Alternatives — Similar Developer Tools Servers

Looking for alternatives to Atlantis? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "atlantis": { "command": "npx", "args": ["-y", "atlantis"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Atlantis?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides