German Family Business Knowledge Graph
About
Query a Neo4j graph database containing a knowledge graph of German family businesses.
Details
- Author
- guangxiangdebizi
- Categories
- Database, Knowledge Base, Other
Jump to
Setup
Install German Family Business Knowledge Graph in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/guangxiangdebizi/KnowledgeGraph-MCP
Follow the installation instructions in the repository README, then restart your MCP client.
Query a Neo4j graph database containing a knowledge graph of German family businesses.
🏢KnowledgeGraph-MCP- 专门为德国家族企业知识图谱构建的 Model Context Protocol (MCP) 服务器
本项目提供一个专业的 MCP 服务器,让 AI 助手(如 Claude、Cursor、Cline 等)能够直接访问和查询德国家族企业知识图谱数据库。通过 Neo4j 图数据库存储结构化知识,支持复杂的关系查询和语义搜索。
- 垂直领域专业化: 专注于德国家族企业领域知识
- 智能查询支持: AI 可自然构造 Cypher 查询语句
- 结构化知识图谱: 层次化组织的企业管理、创新、传承知识
- 即插即用: 快速集成到现有 AI 工作流程
- 安全可靠: 只读访问,防止数据意外修改
- 完整的知识图谱结构概览
- 节点类型、关系类型详细说明
- 实际数据样例展示
- 领域术语和概念介绍
- 企业管理(Unternehmensführung)
- 创新发展(Innovation)
- 企业传承(Nachfolge)
- 治理结构(Governance)
- 中小企业(Mittelstand)
- 数字化转型(Digitalisierung)
- Python 3.8+
- Neo4j 5.0+
- 支持 MCP 的 AI 客户端 (Claude Desktop, Cursor, Cline 等)
git clone https://github.com/guangxiangdebizi/KnowledgeGraph-MCP.git cd KnowledgeGraph-MCP
python -m venv .venv source .venv/bin/activate # Linux/Mac # 或 .venv\Scripts\activate # Windows
# 确保 Neo4j 服务运行在 localhost:7687 # 修改 neo4j_mcp_server.py 中的连接配置 NEO4J_URI = "bolt://localhost:7687" NEO4J_USERNAME = "neo4j" NEO4J_PASSWORD = "your_password"
{ "mcpServers": { "neo4j-knowledge-graph": { "url": "http://127.0.0.1:8000/sse", "name": "Neo4j知识图谱", "description": "德国家族企业知识图谱查询服务" } } }
在~/.config/claude/mcp_servers.json中添加:
{ "mcpServers": { "neo4j-knowledge-graph": { "url": "http://127.0.0.1:8000/sse", "transport": "sse", "name": "Neo4j知识图谱" } } }
KnowledgeGraph-MCP/ ├── neo4j_mcp_server.py # MCP 服务器主程序 ├── import_to_neo4j.py # 数据导入脚本 ├── setup_graphrag.py # GraphRAG 设置脚本 ├── mcp_requirements.txt # MCP 依赖包 ├── requirements.txt # 完整依赖包 ├── knowledge_graph_nodes.csv # 节点数据 ├── knowledge_graph_relationships.csv # 关系数据 ├── 德国的家族企业/ # 原始文档 ├── 德国的家族企业的PPT/ # 演示文档 ├── README_MCP服务器使用说明.md # MCP 使用说明 ├── README_Neo4j导入说明.md # 数据导入说明 ├── cursor_config.json # Cursor MCP 配置 ├── cline_config.json # Cline MCP 配置 └── 通用_mcp_config.json # 通用 MCP 配置
# AI 首先调用此工具了解知识图谱结构 explain_database_structure()
# AI 根据结构信息构造查询 run_cypher_query(""" MATCH (n:Node) WHERE n.name CONTAINS '创新' AND n.type = 'section' RETURN n.name, n.description LIMIT 5 """)
# 查找层次关系 run_cypher_query(""" MATCH (parent)-[:INCLUDES]->(child) WHERE parent.name CONTAINS '家族企业' RETURN parent.name, child.name, child.type """)
- 后端框架:FastMCP 2.0
- 图数据库:Neo4j 5.0+
- Python 驱动:neo4j-driver
- 协议标准:Model Context Protocol
- 传输方式: Server-Sent Events (SSE)
- MCP 服务器使用说明
- Neo4j 数据导入说明
- Model Context Protocol 官方文档
- FastMCP 框架文档
- Fork本项目
- 创建你的特性分支 (git checkout -b feature/AmazingFeature)
- 提交你的更改 (git commit -m 'Add some AmazingFeature')
- 推送到分支 (git push origin feature/AmazingFeature)
- 打开一个Pull Request
- 🔍 扩展知识图谱数据内容
- 🛠️ 增强查询功能和性能
- 📚 完善文档和示例
- 🐛 修复 Bug 和改进代码质量
- 🌐 多语言支持
- 确保 Neo4j 数据库正常运行
- MCP 服务器默认运行在http://127.0.0.1:8000
- 所有查询都是只读的,不支持数据修改操作
- 建议在生产环境中配置适当的安全措施
- Neo4j- 提供强大的图数据库支持
- FastMCP- 优秀的 MCP 框架
- Model Context Protocol- 标准化的 AI 上下文协议
- 📧 提交Issue
- 💬 发起Discussion
- ⭐ 给项目点个 Star 支持我们!
Neo4j graph database server (schema + read/write-cypher) and separate graph database backed memory
Integrate the Neo4j graph database with clients through natural language interactions.
A scalable knowledge graph memory system for LLMs with semantic retrieval and temporal awareness, using Neo4j as a backend.
A knowledge graph memory server using the Neo4j graph database to store and retrieve information from AI interactions.
Transforms raw text into interconnected knowledge graphs and generates insights using a Neo4j database.
Manages personal knowledge using a local Neo4j container, with data imported from JSON files.
Query and interact with FalkorDB graph databases using AI models.
An MCP server for graph-based memory management, enabling AI to create, retrieve, and manage knowledge entities and their relationships.
Query a hybrid graph (Neo4j) and vector (Qdrant) database for powerful semantic and graph-based document retrieval.
MCP memory server with Hebbian learning — concept connections strengthen through co-activation and weaken through disuse.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





