Nexus Memory MCP
Nexus Memory MCP is a persistent semantic memory system designed for AI agents. It can store and retrieve memories semantically, support knowledge graphs and pattern learning, and provide pre - built domain professional knowledge packs to achieve the identity continuity of agents.
rating : 2 points
downloads : 5.7K
What is Nexus Memory MCP?
Nexus Memory MCP is an advanced AI agent memory system that allows AI assistants to remember conversation history, user preferences, and important information, and intelligently recall relevant content in subsequent conversations. Different from traditional keyword - based searches, it uses semantic understanding to find relevant memories, which means that even with different wordings, truly relevant information can be found.How to use Nexus Memory MCP?
Simply install the MCP client and configure the API key, and your AI assistant can gain persistent memory capabilities. The system provides simple tools such as remember, recall, connect, etc., allowing agents to store and retrieve information.Use cases
Suitable for AI assistant scenarios that require long - term memory, such as personal assistants remembering user preferences, development assistants remembering project details, customer service assistants remembering customer history, and educational assistants tracking learning progress, etc.Main features
Semantic memory
A memory and recall system based on meaning rather than keywords, capable of understanding context and intent
Intelligent knowledge packs
Pre - built domain expert knowledge bases that can be activated with one click (e.g., DevOps experts, TCM experts, etc.)
Agent continuity
Maintain the identity and memory continuity of the agent across sessions through the awaken/hibernate function
Knowledge graphs
Automatically create associations between memories and build a structured knowledge network
Pattern learning
Learn user preferences and behavior patterns from historical interactions
Advantages
Strong semantic understanding ability: Search by meaning rather than keywords, more intelligent
Ready - to - use expert knowledge: Built - in domain knowledge packs, quickly gain professional capabilities
Cross - session memory: The agent maintains identity and memory across different sessions
Knowledge association: Automatically discover and establish connections between information
Easy to integrate: One - click installation, compatible with mainstream AI development tools
Limitations
Requires an API key: A subscription service is required after the free trial
Network dependency: Requires connection to a remote API server
Storage limitation: The free version has limited storage space
Learning curve: Requires understanding of the concepts and tools of the memory system
How to use
Get an API key
Register to get a 7 - day free trial API key, including 1000 calls
Install the MCP server
Use npm to install the Nexus Memory MCP server with one click
Configure the client
Add configuration in MCP clients such as Claude Code, Cursor, or Windsurf
Start using
Use memory tools such as remember, recall, etc. in the AI assistant conversation
Usage examples
Remember user preferences
The AI assistant remembers the user's specific preferences and provides personalized responses in subsequent conversations
Activate expert knowledge
Quickly add specific domain professional knowledge to the AI assistant
Cross - session continuity
The AI assistant maintains memory and task status across different work sessions
Project context memory
The development assistant remembers project details, technical decisions, and code structure
Frequently Asked Questions
How is Nexus Memory different from other memory systems?
What does the free trial include?
How is data security ensured?
Which MCP clients are supported?
What are intelligent knowledge packs? How to get more?
How to upgrade the subscription plan?
Related resources
Official documentation
Complete installation, configuration, and usage guide
Nexus market
Purchase subscriptions and intelligent knowledge packs
API reference
Detailed API interface documentation
MCP protocol
Understand the Model Context Protocol standard

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.2K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.4K
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
33.9K
5 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.2K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.0K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.9K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.0K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.3K
4.8 points
