ATLAS, developed by cyanheads, is a Model Context Protocol server that provides hierarchical task management capabilities to Large Language Models. It enables AI assistants to break down complex projects into manageable tasks, track progress, and maintain dependencies within an organized structure. The server implements rich content support, including markdown documentation, code snippets, and structured reasoning documentation. ATLAS stands out by offering a comprehensive task management system tailored for AI-driven project planning and execution. It is particularly useful for applications requiring sophisticated task organization, collaborative AI workflows, or any scenario where an AI system needs to manage and reason about complex, multi-step processes.
Aucun avis encore. Soyez le premier à donner votre avis !
Connectez-vous pour rejoindre la conversation
Highlight AICreates new projects (single/bulk). Parameters: mode ('single'/'bulk'), id (optional client-generated ID for single mode), project details (name, description, status, urls, completionRequirements, dependencies, outputFormat, taskType). For bulk mode, use projects (array of project objects). responseFormat ('formatted'/'json', optional, default: 'formatted').
Lists projects (all/details). Parameters: mode ('all'/'details', default: 'all'), id (for details mode), filters (status, taskType), pagination (page, limit), includes (includeKnowledge, includeTasks), responseFormat ('formatted'/'json', optional, default: 'formatted').
Updates existing projects (single/bulk). Parameters: mode ('single'/'bulk'), id (for single mode), updates object. For bulk mode, use projects (array of objects, each with id and updates). responseFormat ('formatted'/'json', optional, default: 'formatted').
Deletes projects (single/bulk). Parameters: mode ('single'/'bulk'), id (for single mode) or projectIds (array for bulk mode). responseFormat ('formatted'/'json', optional, default: 'formatted').
Creates new tasks (single/bulk). Parameters: mode ('single'/'bulk'), id (optional client-generated ID), projectId, task details (title, description, priority, status, assignedTo, urls, tags, completionRequirements, dependencies, outputFormat, taskType). For bulk mode, use tasks (array of task objects). responseFormat ('formatted'/'json', optional, default: 'formatted').
Updates existing tasks (single/bulk). Parameters: mode ('single'/'bulk'), id (for single mode), updates object. For bulk mode, use tasks (array of objects, each with id and updates). responseFormat ('formatted'/'json', optional, default: 'formatted').
Deletes tasks (single/bulk). Parameters: mode ('single'/'bulk'), id (for single mode) or taskIds (array for bulk mode). responseFormat ('formatted'/'json', optional, default: 'formatted').
Lists tasks for a specific project. Parameters: projectId (required), filters (status, assignedTo, priority, tags, taskType), sorting (sortBy, sortDirection), pagination (page, limit), responseFormat ('formatted'/'json', optional, default: 'formatted').
Adds new knowledge items (single/bulk). Parameters: mode ('single'/'bulk'), id (optional client-generated ID), projectId, knowledge details (text, tags, domain, citations). For bulk mode, use knowledge (array of knowledge objects). responseFormat ('formatted'/'json', optional, default: 'formatted').
Deletes knowledge items (single/bulk). Parameters: mode ('single'/'bulk'), id (for single mode) or knowledgeIds (array for bulk mode). responseFormat ('formatted'/'json', optional, default: 'formatted').
Lists knowledge items for a specific project. Parameters: projectId (required), filters (tags, domain, search), pagination (page, limit), responseFormat ('formatted'/'json', optional, default: 'formatted').
Performs unified search across entities. Parameters: value (search term, required), property (optional: if specified, performs regex search on this property; if omitted, performs full-text search), filters (entityTypes, taskType, assignedToUserId), options (caseInsensitive (default: true, for regex), fuzzy (default: false, for regex 'contains' or full-text Lucene fuzzy)), pagination (page, limit), responseFormat ('formatted'/'json', optional, default: 'formatted').
Initiates a structured deep research process by creating a hierarchical plan within the Atlas knowledge base. Parameters: projectId (required), researchTopic (required), researchGoal (required), scopeDefinition (optional), subTopics (required array of objects, each with question (required), initialSearchQueries (optional array), nodeId (optional), priority (optional), assignedTo (optional), initialStatus (optional, default: 'todo')), researchDomain (optional), initialTags (optional), planNodeId (optional), createTasks (optional, default: true), responseFormat ('formatted'/'json', optional, default: 'formatted').
Completely resets the database, removing all projects, tasks, and knowledge. Parameters: acknowledgement (must be set to true to confirm, required), responseFormat ('formatted'/'json', optional, default: 'formatted').
