Atlas MCP Server 1ac6a77a

MCP文档知识

提供方 LiuBBaby

文档知识 未标注 API Key 社区 / 第三方 Claude DesktopClaude

ATLAS是一个基于Model Context Protocol (MCP)的项目、任务和知识管理系统,专为LLM代理设计,支持项目跟踪、任务生命周期管理和知识整合。

一句话选型结论

按资料字段整理

Atlas MCP Server 1ac6a77a 属于文档知识类 MCP 服务器,传输方式未标注,API Key,可直接接入 Claude Desktop、Claude,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式未标注 鉴权API Key 部署方式未标注
GitHub 星标 0 仓库热度,无公开仓库时显示未标注
工具数 14 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量14暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

项目管理TypeScript本地部署任务管理知识管理LLM代理Neo4j数据库

安装与配置

未标注 API Key
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 14 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 14 个工具,覆盖面较广,能满足多种调用。
  • 已适配 Claude Desktop、Claude,换客户端不用重新研究配置。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Atlas MCP Server 1ac6a77a当前 14 未标注 未标注 无 2026-05-17
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方LiuBBaby上游标注的维护方 LiuBBaby
分类文档知识本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

27.8 KB
来自项目仓库与上游目录的原文,未做删改

ATLAS: Task Management System

ATLAS (Adaptive Task & Logic Automation System) is a project, knowledge, and task management system for LLM Agents.

Built on a three-tier architecture:```
+------------------------------------------+
| PROJECT |
|------------------------------------------|
| id: string |
| name: string |
| description: string |
| status: string |
| urls?: Array<{title: string, url: string}>|
| completionRequirements: string |
| outputFormat: string |
| taskType: string |
| createdAt: string |
| updatedAt: string |
+----------------+-------------------------+
| |
| |
v v
+----------------------------------+ +----------------------------------+
| TASK | | KNOWLEDGE |
|----------------------------------| |----------------------------------|
| id: string | | id: string |
| projectId: string | | projectId: string |
| title: string | | text: string |
| description: string | | tags?: string[] |
| priority: string | | domain: string |
| status: string | | citations?: string[] |
| assignedTo?: string | | createdAt: string |
| urls?: Array<{title: string, | | |
| url: string}> | | updatedAt: string |
| tags?: string[] | | |
| completionRequirements: string | | |
| outputFormat: string | | |
| taskType: string | | |
| createdAt: string | | |
| updatedAt: string | | |
+----------------------------------+ +----------------------------------+


Implemented as a Model Context Protocol (MCP) server, ATLAS allows LLM agents to interact with a project management database, enabling them to manage projects, tasks, and knowledge items.

&gt; **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:
&gt;
&gt; - Self-hosting using Docker (docker-compose included in repository)
&gt; - Using Neo4j AuraDB cloud service: https://neo4j.com/product/auradb/
&gt;
&gt; Version 2.5.0 introduces a new 3-node system (Projects, Tasks, Knowledge) that replaces the previous structure.

## Table of Contents

- Overview
- Features
- Installation
- Running the Server
- Web UI (Experimental)
- Configuration
- Project Structure
- Tools
- Resources
- Database Backup and Restore
- Examples
- License

## Overview

ATLAS implements the Model Context Protocol (MCP), enabling standardized communication between LLMs and external systems through:

- **Clients**: Claude Desktop, IDEs, and other MCP-compatible clients
- **Servers**: Tools and resources for project, task, and knowledge management
- **LLM Agents**: AI models that leverage the server&#x27;s management capabilities

### System Integration

The Atlas Platform integrates these components into a cohesive system:

- **Project-Task Relationship**: Projects contain tasks that represent actionable steps needed to achieve project goals. Tasks inherit context from their parent project while providing granular tracking of individual work items.
- **Knowledge Integration**: Both projects and tasks can be enriched with knowledge items, providing team members with necessary information and context.
- **Dependency Management**: Both projects and tasks support dependency relationships, allowing for complex workflows with prerequisites and sequential execution requirements.
- **Unified Search**: The platform provides cross-entity search capabilities, allowing users to find relevant projects, tasks, or knowledge based on various criteria.

## Features

### Project Management

- **Comprehensive Tracking:** Manage project metadata, statuses, and rich content (notes, links, etc.) with built-in support for bulk operations.
- **Dependency &amp; Relationship Handling:** Automatically validate and track inter-project dependencies.

### Task Management

- **Task Lifecycle Management:** Create, track, and update tasks through their entire lifecycle.
- **Prioritization &amp; Categorization:** Assign priority levels and categorize tasks with tags for better organization.
- **Dependency Tracking:** Establish task dependencies to create structured workflows.

### Knowledge Management

- **Structured Knowledge Repository:** Maintain a searchable repository of project-related information.
- **Domain Categorization:** Organize knowledge by domain and tags for easy retrieval.
- **Citation Support:** Track sources and references for knowledge items.

### Graph Database Integration

- **Native Relationship Management:** Leverage Neo4j&#x27;s ACID-compliant transactions and optimized queries for robust data integrity.
- **Advanced Search &amp; Scalability:** Perform property-based searches with fuzzy matching and wildcards while maintaining high performance.

### Unified Search

- **Cross-Entity Search:** Find relevant projects, tasks, or knowledge based on content, metadata, or relationships.
- **Flexible Query Options:** Support for case-insensitive, fuzzy, and advanced filtering options.

## Installation

1.  **Clone the repository:**```bash
    git clone https://github.com/cyanheads/atlas-mcp-server.git
    cd atlas-mcp-server
    ```

2.  **Install dependencies:**```bash
    npm install
    ```

3.  **Configure Neo4j:**
    Ensure you have a Neo4j instance running and accessible. You can start one using the provided Docker configuration:```bash
    docker-compose up -d
    ```

    Update your `.env` file with the Neo4j connection details (see Configuration).

4.  **Build the project:**```bash
    npm run build
    ```

## Running the Server

Most MCP Clients run the server automatically, but you can also run it manually for testing or development purposes using the following commands.

ATLAS MCP Server supports multiple transport mechanisms for communication:

- **Standard I/O (stdio):** This is the default mode and is typically used for direct integration with local MCP clients (like IDE extensions).```bash
  npm run start:stdio
  ```

  This uses the `MCP_TRANSPORT_TYPE=stdio` setting.

- **Streamable HTTP:** This mode allows the server to listen for MCP requests over HTTP, suitable for remote clients or web-based integrations.```bash
  npm run start:http
  ```

  This uses the `MCP_TRANSPORT_TYPE=http` setting. The server will listen on the host and port defined in your `.env` file (e.g., `MCP_HTTP_HOST` and `MCP_HTTP_PORT`, defaulting to `127.0.0.1:3010`). Ensure your firewall allows connections if accessing remotely.

## Web UI (Experimental)

A basic Web UI is available for viewing Project, Task, &amp; Knowledge details.

- **Opening the UI**:

  - To open the UI directly in your browser, run the following command in your terminal:```bash
    npm run webui
    ```

- **Functionality**:
  - You can see an example screenshot of the Web UI here.

## Configuration

### Environment Variables

Environment variables should be set in the client config in your MCP Client, or in a `.env` file in the project root for local development.```bash
# Neo4j Configuration
NEO4J_URI=bolt://localhost:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=password2

# Application Configuration
MCP_LOG_LEVEL=debug # Minimum logging level. Options: emerg, alert, crit, error, warning, notice, info, debug. Default: &quot;debug&quot;.
LOGS_DIR=./logs # Directory for log files. Default: &quot;./logs&quot; in project root.
NODE_ENV=development # &#x27;development&#x27; or &#x27;production&#x27;. Default: &quot;development&quot;.

# MCP Transport Configuration
MCP_TRANSPORT_TYPE=stdio # &#x27;stdio&#x27; or &#x27;http&#x27;. Default: &quot;stdio&quot;.
MCP_HTTP_HOST=127.0.0.1 # Host for HTTP transport. Default: &quot;127.0.0.1&quot;.
MCP_HTTP_PORT=3010 # Port for HTTP transport. Default: 3010.
# MCP_ALLOWED_ORIGINS=http://localhost:someport,https://your-client.com # Optional: Comma-separated list of allowed origins for HTTP CORS.

# MCP Security Configuration
# MCP_AUTH_SECRET_KEY=your_very_long_and_secure_secret_key_min_32_chars # Optional: Secret key (min 32 chars) for JWT authentication if HTTP transport is used. CRITICAL for production. *Note: Production environment use has not been tested yet.*
MCP_RATE_LIMIT_WINDOW_MS=60000 # Rate limit window in milliseconds. Default: 60000 (1 minute).
MCP_RATE_LIMIT_MAX_REQUESTS=100 # Max requests per window per IP for HTTP transport. Default: 100.

# Database Backup Configuration
BACKUP_MAX_COUNT=10 # Maximum number of backup sets to keep. Default: 10.
BACKUP_FILE_DIR=./atlas-backups # Directory where backup files will be stored (relative to project root). Default: &quot;./atlas-backups&quot;.

# OpenRouter LLM Configuration (Optional - additional parameters present in `src/config/index.ts`)
# OPENROUTER_API_KEY=your_openrouter_api_key # API key for OpenRouter services.
LLM_DEFAULT_MODEL=&quot;google/gemini-2.5-flash-preview:thinking&quot; # Default LLM model.

Refer to src/config/index.ts for all available environment variables, their descriptions, and default values.

MCP Client Settings

How you configure your MCP client depends on the client itself and the chosen transport type. An mcp.json file in the project root can be used by some clients (like mcp-inspector) to define server configurations; update as needed.

For Stdio Transport (Example Configuration):```json
{
"mcpServers": {
"atlas-mcp-server-stdio": {
"command": "node",
"args": ["/full/path/to/atlas-mcp-server/dist/index.js"],
"env": {
"NEO4J_URI": "bolt://localhost:7687",
"NEO4J_USER": "neo4j",
"NEO4J_PASSWORD": "password2",
"MCP_LOG_LEVEL": "info",
"NODE_ENV": "production",
"MCP_TRANSPORT_TYPE": "stdio"
}
}
}
}


**For Streamable HTTP (Example Configuration):**
If your client supports connecting to an MCP server via Streamable HTTP, you provide the server&#x27;s endpoint (e.g., `http://localhost:3010/mcp`) in your client configuration.```json
{
  &quot;mcpServers&quot;: {
    &quot;atlas-mcp-server-http&quot;: {
      &quot;command&quot;: &quot;node&quot;,
      &quot;args&quot;: [&quot;/full/path/to/atlas-mcp-server/dist/index.js&quot;],
      &quot;env&quot;: {
        &quot;NEO4J_URI&quot;: &quot;bolt://localhost:7687&quot;,
        &quot;NEO4J_USER&quot;: &quot;neo4j&quot;,
        &quot;NEO4J_PASSWORD&quot;: &quot;password2&quot;,
        &quot;MCP_LOG_LEVEL&quot;: &quot;info&quot;,
        &quot;NODE_ENV&quot;: &quot;production&quot;,
        &quot;MCP_TRANSPORT_TYPE&quot;: &quot;http&quot;,
        &quot;MCP_HTTP_PORT&quot;: &quot;3010&quot;,
        &quot;MCP_HTTP_HOST&quot;: &quot;127.0.0.1&quot;
        // &quot;MCP_AUTH_SECRET_KEY&quot;: &quot;your-secure-token&quot; // If authentication is enabled on the server
      }
    }
  }
}

Note: Always use absolute paths for args when configuring client commands if the server is not in the client's immediate working directory. The MCP_AUTH_SECRET_KEY in the client's env block is illustrative; actual token handling for client-to-server communication would depend on the client's capabilities and the server's authentication mechanism (e.g., sending a JWT in an Authorization header).

Project Structure

The codebase follows a modular structure:src/ ├── config/ # Configuration management (index.ts) ├── index.ts # Main server entry point ├── mcp/ # MCP server implementation (server.ts) │ ├── resources/ # MCP resource handlers (index.ts, types.ts, knowledge/, projects/, tasks/) │ └── tools/ # MCP tool handlers (individual tool directories) ├── services/ # Core application services │ ├── llm-providers/ # LLM provider integrations (e.g., OpenRouter) │ └── neo4j/ # Neo4j database services (index.ts, driver.ts, backupRestoreService.ts, etc.) ├── types/ # Shared TypeScript type definitions (errors.ts, mcp.ts, tool.ts) └── utils/ # Utility functions and internal services (e.g., logger, errorHandler, sanitization)

Tools

ATLAS provides a comprehensive suite of tools for project, task, and knowledge management, callable via the Model Context Protocol.

Project Operations

Tool Name Description Key Arguments
atlas_project_create Creates new projects (single/bulk). 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').
atlas_project_list Lists projects (all/details). mode ('all'/'details', default: 'all'), id (for details mode), filters (status, taskType), pagination (page, limit), includes (includeKnowledge, includeTasks), responseFormat ('formatted'/'json', optional, default: 'formatted').
atlas_project_update Updates existing projects (single/bulk). 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').
atlas_project_delete Deletes projects (single/bulk). mode ('single'/'bulk'), id (for single mode) or projectIds (array for bulk mode). responseFormat ('formatted'/'json', optional, default: 'formatted').

Task Operations

Tool Name Description Key Arguments
atlas_task_create Creates new tasks (single/bulk). 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').
atlas_task_update Updates existing tasks (single/bulk). 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').
atlas_task_delete Deletes tasks (single/bulk). mode ('single'/'bulk'), id (for single mode) or taskIds (array for bulk mode). responseFormat ('formatted'/'json', optional, default: 'formatted').
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, default: 'formatted').

Knowledge Operations

Tool Name Description Key Arguments
atlas_knowledge_add Adds new knowledge items (single/bulk). 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').
atlas_knowledge_delete Deletes knowledge items (single/bulk). mode ('single'/'bulk'), id (for single mode) or knowledgeIds (array for bulk mode). responseFormat ('formatted'/'json', optional, default: 'formatted').
atlas_knowledge_list Lists knowledge items for a specific project. projectId (required), filters (tags, domain, search), pagination (page, limit), responseFormat ('formatted'/'json', optional, default: 'formatted').

Search Operations

Tool Name Description Key Arguments
atlas_unified_search Performs unified search across entities. 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').

Research Operations

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 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').

Database Operations

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, required), responseFormat ('formatted'/'json', optional, default: 'formatted').

Resources

ATLAS exposes project, task, and knowledge data through standard MCP resource endpoints.

Direct Resources

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 Templates

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).

Database Backup and Restore

ATLAS provides functionality to back up and restore the Neo4j database content. The core logic resides in src/services/neo4j/backupRestoreService.ts.

Backup Process

  • Mechanism: The backup process exports all Project, Task, and Knowledge nodes, along with their relationships, into separate JSON files. A full-export.json containing all data is also created.
  • Output: Each backup creates a timestamped directory (e.g., atlas-backup-YYYYMMDDHHMMSS) within the configured backup path (default: ./atlas-backups/). This directory contains projects.json, tasks.json, knowledge.json, relationships.json, and full-export.json.
  • Manual Backup: You can trigger a manual backup using the provided script:bash npm run db:backup
    This command executes scripts/db-backup.ts, which calls the exportDatabase function.

Restore Process

  • Mechanism: The restore process first completely clears the existing Neo4j database. Then, it imports nodes and relationships from the JSON files located in the specified backup directory. It prioritizes full-export.json if available.
  • Warning: Restoring from a backup is a destructive operation. It will overwrite all current data in your Neo4j database.
  • Manual Restore: To restore the database from a backup directory, use the import script:bash npm run db:import &lt;path_to_backup_directory&gt;
    Replace ` with the actual path to the backup folder (e.g.,./atlas-backups/atlas-backup-20250326120000). This command executesscripts/db-import.ts, which calls theimportDatabase` function.
  • Relationship Handling: The import process attempts to recreate relationships based on the id properties stored within the nodes during export. Ensure your nodes have consistent id properties for relationships to be restored correctly.

Examples

The examples/ directory contains practical examples demonstrating various features of the ATLAS MCP Server.

  • Backup Example: Located in 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.
  • Deep Research Example: Located in 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.

License

Apache License 2.0


Built with the Model Context Protocol

常见问题

6 问
答案由本站依据条目字段整理,不引用上游原文
Atlas MCP Server 1ac6a77a 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Atlas MCP Server 1ac6a77a 怎么在 Claude Desktop、Claude 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Atlas MCP Server 1ac6a77a 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Atlas MCP Server 1ac6a77a 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

Atlas MCP Server 1ac6a77a 支持哪些客户端?

资料标注支持 Claude Desktop、Claude;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Atlas MCP Server 1ac6a77a 能提供哪些能力?

资料显示约 14 个工具;能力标签包括 知识管理、LLM代理、TypeScript、Claude。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。