ATLAS

Provides hierarchical task management and ACID-safe operations for LLM workflows via MCP.
  • typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "mcp-mirror-cyanheads_atlas-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/atlas-mcp-server/build/index.js"
      ],
      "env": {
        "NODE_ENV": "production",
        "ATLAS_STORAGE_DIR": "/path/to/storage/directory",
        "ATLAS_STORAGE_NAME": "atlas-tasks"
      }
    }
  }
}

ATLAS MCP Server provides hierarchical task management and ACID-safe operations for Large Language Models through the Model Context Protocol. It offers structured task organization, strict validation, and reliable persistence so you can coordinate complex tasks and dependencies across LLM-driven workflows.

How to use

You connect your MCP client to the Atlas MCP Server to manage tasks, dependencies, and metadata for long-running LLM-driven projects. Use the server to create, update, and query tasks, validate paths and relationships, and perform bulk operations with transactional safety. Leverage hierarchical task structures (TASK, GROUP, MILESTONE) to model work, enforce dependency constraints, and track progress with rich metadata.

How to install

Prerequisites: you need Node.js installed on your machine.

  1. Clone the Atlas MCP Server repository.

  2. Install dependencies.

  3. Build and run the server.

Configuration

{
  "mcpServers": {
    "atlas": {
      "command": "node",
      "args": ["/path/to/atlas-mcp-server/build/index.js"],
      "env": {
        "ATLAS_STORAGE_DIR": "/path/to/storage/directory",
        "ATLAS_STORAGE_NAME": "atlas-tasks",
        "NODE_ENV": "production"
      }
    }
  }
}

Task structure, tools, and usage notes

The server supports a rich task model with hierarchical relationships, ACID-compliant operations, and robust validation. Use it to model work with clear parent-child relationships, dependencies, and metadata. You can perform create, update, and bulk operations with transactional safety, validate path rules, and prevent circular dependencies.

Maintenance and best practices

Monitor health, memory usage, and database statistics. Use bulk updates for efficiency, validate inputs, and maintain clean task hierarchies. Regularly review metadata for consistency and use transactions for related changes.

Troubleshooting and notes

If you encounter issues with transactions or bulk operations, verify your dependencies and path validations, and check the environment configuration used when launching Atlas MCP Server.

Available tools

create_task

Creates a new task or group with validation and dependency checks, enforcing path rules and metadata schemas.

update_task

Updates task fields with validation for status transitions and dependency changes, ensuring ACID safety.

bulk_task_operations

Executes multiple task operations atomically, providing transactional integrity for bulk changes.

vacuum_database

Optimizes the database and updates statistics to maintain performance.

repair_relationships

Repairs inconsistencies in task relationships and validates path patterns.

clear_all_tasks

Resets the task database with safety checks to prevent accidental data loss.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational