ATLAS uses .ENV files for configuration management, with support for creating a .env file based on the provided .env.example template.
ATLAS integrates with Docker for simplified installation and running of Neo4j. Docker-compose is included in the repository for self-hosting the Neo4j database.
ATLAS Skills system includes git integration, with configuration options for GitHub username and email available through environment variables.
ATLAS (Adaptive Task & Logic Automation System) is a project, knowledge, and task management system for LLM Agents.
Built on a three-tier architecture:
Implemented as a Model Context Protocol (MCP) server, ATLAS allows LLM agents to interact with project management database, enabling managing projects, tasks, and knowledge items.
Important Version Note: Version 1.5.4 is the last version that uses SQLite as the database. Version 2.0 and onwards has been completely rewritten to use Neo4j, which requires either:
- Self-hosting using Docker (docker-compose included in repository)
- Using Neo4j AuraDB cloud service: https://neo4j.com/product/auradb/
Version 2.5.0 introduces a new 3-node system (Projects, Tasks, Knowledge) that replaces the previous structure.
ATLAS implements the Model Context Protocol (MCP), enabling standardized communication between LLMs and external systems through:
The Atlas Platform integrates these components into a cohesive system:
Create a .env file based on .env.example:
Add to your MCP client settings:
The codebase follows a modular structure:
Note: ID generation logic is primarily located in src/services/neo4j/helpers.ts.
ATLAS provides a comprehensive suite of tools for project, task, and knowledge management, callable via the Model Context Protocol.
| Tool Name | Description | Key Arguments |
|---|---|---|
atlas_project_create | Creates new projects (single/bulk). | mode ('single'/'bulk'), project details (name, description, status, urls, completionRequirements, dependencies, outputFormat, taskType), responseFormat ('formatted'/'json', optional). |
atlas_project_list | Lists projects (all/details). | mode ('all'/'details'), id (for details), filters (status, taskType), pagination (page, limit), includes (includeKnowledge, includeTasks), responseFormat ('formatted'/'json', optional). |
atlas_project_update | Updates existing projects (single/bulk). | mode ('single'/'bulk'), id, updates object, responseFormat ('formatted'/'json', optional). Bulk mode uses projects array. |
atlas_project_delete | Deletes projects (single/bulk). | mode ('single'/'bulk'), id (single) or projectIds array (bulk), responseFormat ('formatted'/'json', optional). |
| Tool Name | Description | Key Arguments |
|---|---|---|
atlas_task_create | Creates new tasks (single/bulk). | mode ('single'/'bulk'), projectId, task details (title, description, priority, status, assignedTo, tags, completionRequirements, dependencies, outputFormat, taskType), responseFormat ('formatted'/'json', optional). |
atlas_task_update | Updates existing tasks (single/bulk). | mode ('single'/'bulk'), id, updates object, responseFormat ('formatted'/'json', optional). Bulk mode uses tasks array. |
atlas_task_delete | Deletes tasks (single/bulk). | mode ('single'/'bulk'), id (single) or taskIds array (bulk), responseFormat ('formatted'/'json', optional). |
atlas_task_list | Lists tasks for a specific project. | projectId (required), filters (status, assignedTo, priority, tags, taskType), sorting (sortBy, sortDirection), pagination (page, limit), responseFormat ('formatted'/'json', optional). |
| Tool Name | Description | Key Arguments |
|---|---|---|
atlas_knowledge_add | Adds new knowledge items (single/bulk). | mode ('single'/'bulk'), projectId, knowledge details (text, tags, domain, citations), responseFormat ('formatted'/'json', optional). Bulk mode uses knowledge array. |
atlas_knowledge_delete | Deletes knowledge items (single/bulk). | mode ('single'/'bulk'), id (single) or knowledgeIds array (bulk), responseFormat ('formatted'/'json', optional). |
atlas_knowledge_list | Lists knowledge items for a specific project. | projectId (required), filters (tags, domain, search), pagination (page, limit), responseFormat ('formatted'/'json', optional). |
| Tool Name | Description | Key Arguments |
|---|---|---|
atlas_unified_search | Performs unified search across entities. | value (search term), property (optional), filters (entityTypes, taskType), options (caseInsensitive, fuzzy), pagination (page, limit), responseFormat ('formatted'/'json', optional). |
| Tool Name | Description | Key Arguments |
|---|---|---|
atlas_deep_research | Initiates a structured deep research process by creating a hierarchical plan within the Atlas knowledge base. | projectId (required), researchTopic (required), researchGoal (required), scopeDefinition (optional), subTopics (required array with questions and search queries), researchDomain (optional), initialTags (optional), planNodeId (optional), responseFormat (optional). |
| Tool Name | Description | Key Arguments |
|---|---|---|
atlas_database_clean | Destructive: Completely resets the database, removing all projects, tasks, and knowledge. | acknowledgement (must be set to true to confirm), responseFormat ('formatted'/'json', optional). |
ATLAS exposes project, task, and knowledge data through standard MCP resource endpoints.
| Resource Name | Description |
|---|---|
atlas://projects | List of all projects in the Atlas platform with pagination support. |
atlas://tasks | List of all tasks in the Atlas platform with pagination and filtering support. |
atlas://knowledge | List of all knowledge items in the Atlas platform with pagination and filtering support. |
| Resource Name | Description |
|---|---|
atlas://projects/{projectId} | Retrieves a single project by its unique identifier (projectId). |
atlas://tasks/{taskId} | Retrieves a single task by its unique identifier (taskId). |
atlas://projects/{projectId}/tasks | Retrieves all tasks belonging to a specific project (projectId). |
atlas://knowledge/{knowledgeId} | Retrieves a single knowledge item by its unique identifier (knowledgeId). |
atlas://projects/{projectId}/knowledge | Retrieves all knowledge items belonging to a specific project (projectId). |
ATLAS provides functionality to back up and restore the Neo4j database content. The core logic resides in src/services/neo4j/backupRestoreService.ts.
Important: The automatic backup functionality has been removed due to inefficiency. The call to triggerBackgroundBackup in src/services/neo4j/driver.ts is commented out with a note indicating it was removed. Please use the manual backup process described below to protect your data.
Project, Task, and Knowledge nodes, along with their relationships, into separate JSON files.atlas-backup-YYYYMMDDHHMMSS) within the configured backup path (default: ./atlas-backups/). This directory contains projects.json, tasks.json, knowledge.json, and relationships.json.scripts/db-backup.ts, which calls the exportDatabase function.<path_to_backup_directory> with the actual path to the backup folder (e.g., ./atlas-backups/atlas-backup-20250326120000). This command executes scripts/db-import.ts, which calls the importDatabase function.id properties stored within the nodes during export. Ensure your nodes have consistent id properties for relationships to be restored correctly.The examples/ directory contains practical examples demonstrating various features of the ATLAS MCP Server.
examples/backup-example/, this shows the structure and format of the JSON files generated by the npm run db:backup command. See the Examples README for more details.examples/deep-research-example/, this demonstrates the output and structure generated by the atlas_deep_research tool. It includes a markdown file (covington_community_grant_research.md) summarizing the research plan and a JSON file (full-export.json) containing the raw data exported from the database after the research plan was created. See the Examples README for more details.For bugs and feature requests, please create an issue.
Apache License 2.0
You must be authenticated.
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 and dependencies.