ATLAS

v1.0.0Coding Agentsstable

ATLAS (Adaptive Task & Logic Automation System) is a Model Context Protocol server that provides hierarchical task management capabilities to Large Language Models. This tool provides LLMs with the structure and context needed to manage complex tasks

agentsaideep-researchgraph-databasellm
Share:
475
Stars
0
Downloads
0
Weekly
0/5

What is ATLAS?

ATLAS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to atlas (adaptive task & logic automation system) is a model context protocol server that provides hierarchical task management capabilities to large language models. this tool provides llms with the st...

ATLAS (Adaptive Task & Logic Automation System) is a Model Context Protocol server that provides hierarchical task management capabilities to Large Language Models. This tool provides LLMs with the structure and context needed to manage complex tasks

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

Features

  • ATLAS (Adaptive Task & Logic Automation System) is a Model C

Use Cases

Hierarchical task management
Agent-powered task automation
Deep research coordination
cyanheads

Maintainer

LicenseApache 2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y atlas

Manual Installation

npx -y atlas

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 ATLAS

ATLAS (Adaptive Task & Logic Automation System) is an MCP server that brings hierarchical task and project management to LLMs through a Neo4j graph database backend. It exposes structured tools for creating projects, decomposing them into tasks, attaching knowledge nodes, and running deep research queries—giving AI agents the persistent memory and organizational scaffolding they need to manage long-running, multi-step work. Developers use ATLAS to supercharge Claude and other LLMs with durable project context that survives across sessions and can be queried, searched, and updated programmatically.

Prerequisites

  • Node.js 18+ and npm installed
  • Docker and Docker Compose for running the Neo4j graph database
  • An MCP-compatible client such as Claude Desktop or Cursor
  • Git for cloning the repository
1

Clone the repository

Clone the ATLAS MCP server repository to your machine.

git clone https://github.com/cyanheads/atlas-mcp-server.git
cd atlas-mcp-server
2

Start the Neo4j database

Launch Neo4j using Docker Compose. ATLAS requires a running Neo4j instance to store projects, tasks, and knowledge nodes persistently.

docker-compose up -d
3

Configure environment variables

Create a .env file or export the required variables. Set NEO4J_URI, NEO4J_USER, and NEO4J_PASSWORD to match your Neo4j instance. The Docker Compose default password is 'password2'.

export NEO4J_URI=bolt://localhost:7687
export NEO4J_USER=neo4j
export NEO4J_PASSWORD=password2
export MCP_TRANSPORT_TYPE=stdio
4

Install dependencies and build

Install npm dependencies and compile the TypeScript source to prepare the server for running.

npm install
npm run build
5

Start the MCP server

Start ATLAS in stdio mode for use with Claude Desktop, or HTTP mode if you need a network-accessible endpoint.

npm run start:stdio
# Or for HTTP mode:
npm run start:http
6

Connect your MCP client

Add ATLAS to your Claude Desktop configuration file and restart the client to load the project and task management tools.

ATLAS Examples

Client configuration

Claude Desktop configuration to connect to the ATLAS MCP server running in stdio mode. The server binary is built from source in the dist directory.

{
  "mcpServers": {
    "atlas": {
      "command": "node",
      "args": ["/absolute/path/to/atlas-mcp-server/dist/index.js"],
      "env": {
        "NEO4J_URI": "bolt://localhost:7687",
        "NEO4J_USER": "neo4j",
        "NEO4J_PASSWORD": "password2",
        "MCP_TRANSPORT_TYPE": "stdio",
        "NODE_ENV": "production"
      }
    }
  }
}

Prompts to try

Use these prompts with Claude to interact with the ATLAS project and task management system.

- "Create a new project called 'API Redesign' with a description of its goals"
- "List all tasks in the API Redesign project"
- "Add a task to research authentication patterns and set its priority to high"
- "Search all projects and tasks for anything related to database migrations"
- "Add a knowledge node about the chosen database schema to the API Redesign project"

Troubleshooting ATLAS

Server fails to start with Neo4j connection refused

Ensure Neo4j is running with `docker-compose ps`. The bolt port (7687) must be accessible. Wait a few seconds after `docker-compose up -d` for Neo4j to finish initializing before starting ATLAS.

Authentication failed when connecting to Neo4j

The Docker Compose default password is 'password2' (not the standard 'neo4j'). Check your NEO4J_PASSWORD environment variable matches what is set in the docker-compose.yml file.

MCP tools are not visible in Claude Desktop

Verify the absolute path to dist/index.js in your config is correct and that you ran `npm run build` successfully. Restart Claude Desktop fully after editing the config file.

Frequently Asked Questions about ATLAS

What is ATLAS?

ATLAS is a Model Context Protocol (MCP) server that atlas (adaptive task & logic automation system) is a model context protocol server that provides hierarchical task management capabilities to large language models. this tool provides llms with the structure and context needed to manage complex tasks It connects AI assistants to external tools and data sources through a standardized interface.

How do I install ATLAS?

Install via npm with the command: npx -y atlas. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with ATLAS?

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

Is ATLAS free to use?

Yes, ATLAS is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

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

Quick Config Preview

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

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

Read the full setup guide →

Ready to use ATLAS?

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