
一台先进的MCP服务器,通过具备能力的知识图谱实现。该服务器通过语义搜索、文档处理和混合检索扩展了基本内存概念,以实现更多......
概览
一台先进的MCP服务器,通过具备能力的知识图示。该服务器通过语义搜索、文档处理和混合检索扩展了基本内存概念,实现更智能的内存管理。 来自模型上下文协议项目的知识图谱记忆服务器。 该服务器设计用于与 MCP 客户端(例如 Claude Desktop、VS Code)本地运行,并需要本地文件系统访问以实现数据库存储。 - : 持久实体、关系和观察 - : 使用句子变换器进行语义相似性搜索 - : 支持RAG的文档分块和嵌入 - : 结合向量相似性与图遍历 - : 快速本地存储,支持向量操作 sqlite-vec - : 自动从文档中提取词 该服务器通过模型上下文协议(MCP)提供全面的内存管理: - storeDocument:存储带有元数据的文档以便处理- chunkDocument:创建带有可配置参数的文本块-...
概述(AI 翻译)
一个先进的MCP服务器,支持RAG支持的内存,通过具备向量搜索功能的知识图。该服务器通过语义搜索、文档处理和混合检索扩展了基本内存概念,实现更智能的内存管理。
灵感来源: 模型上下文协议项目中的知识图谱内存服务器。
注: 该服务器设计为与MCP客户端(如Claude Desktop、VS Code)本地运行,并需要本地文件系统访问以实现数据库存储。
✨ 主要特色
- ** 🧠 知识图谱记忆**:持久实体、关系和观察
- ** 🔍 向量搜索**:使用句子变换器进行语义相似性搜索
- ** 📄 文档处理**:支持RAG的文档分块与嵌入
- ** 🔗 混合搜索:结合向量相似性与图遍历
- ** ⚡ SQLite 后端**:支持快速本地存储,支持 sqlite-vec 进行向量操作
- ** 🎯 实体提取**:自动从文档中提取术语
工具
该服务器通过模型上下文协议(MCP)提供全面的内存管理:
📚 文档管理
storeDocument:存储带有元数据的文档以便处理
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
rag-memory-mcp
An advanced MCP server for RAG-enabled memory through a knowledge graph with vector search capabilities. This server extends the basic memory concepts with semantic search, document processing, and hybrid retrieval for more intelligent memory management.
Inspired by: Knowledge Graph Memory Server from the Model Context Protocol project.
Note: This server is designed to run locally alongside MCP clients (e.g., Claude Desktop, VS Code) and requires local file system access for database storage.
✨ Key Features
- 🧠 Knowledge Graph Memory: Persistent entities, relationships, and observations
- 🔍 Vector Search: Semantic similarity search using sentence transformers
- 📄 Document Processing: RAG-enabled document chunking and embedding
- 🔗 Hybrid Search: Combines vector similarity with graph traversal
- ⚡ SQLite Backend: Fast local storage with sqlite-vec for vector operations
- 🎯 Entity Extraction: Automatic term extraction from documents
Tools
This server provides comprehensive memory management through the Model Context Protocol (MCP):
📚 Document Management
storeDocument: Store documents with metadata for processingchunkDocument: Create text chunks with configurable parametersembedChunks: Generate vector embeddings for semantic searchextractTerms: Extract potential entity terms from documentslinkEntitiesToDocument: Create explicit entity-document associationsdeleteDocuments: Remove documents and associated datalistDocuments: View all stored documents with metadata
🧠 Knowledge Graph
createEntities: Create new entities with observations and typescreateRelations: Establish relationships between entitiesaddObservations: Add contextual information to existing entitiesdeleteEntities: Remove entities and their relationshipsdeleteRelations: Remove specific relationshipsdeleteObservations: Remove specific observations from entities
🔍 Search & Retrieval
hybridSearch: Advanced search combining vector similarity and graph traversalsearchNodes: Find entities by name, type, or observation contentopenNodes: Retrieve specific entities and their relationships
安装
npx -y rag-memory-mcp配置
{
"mcpServers": {
"rag-memory": {
"command": "npx",
"args": ["-y", "rag-memory-mcp"]
}
}
}