Neo4j MCP 为 AI 助手和基于大型语言模型（LLM）的工具提供直接、结构化访问您的 Neo4j 图数据库。 通过实现模型上下文协议（MCP），它作为任何兼容MCP客户端（如支持MCP的Claude、光标或VS Code）与Neo4j实例之间的桥梁。

特色

• 探索你的图模式——发现节点标签、关系类型和属性键
• 让AI在没有事先知识的情况下推理你的数据模型
• 运行密码查询——根据自然语言提示对数据库执行、读取和写入查询
• 检查和分析数据——检索节点、关系和路径，以回答问题、生成摘要或将数据传递给其他工作流程

工具

• get-schema — 内省标签、关系类型、属性键
• [read-cypher — 执行不修改数据库数据的只读密码查询，通过 EXPLAIN 和 Neo4j 的查询类型分类强制执行。注意： Neo4j 错误将自定义过程或函数分类为只读，可能会绕过此检查;确保分类正确的责任由过程/函数维护者负责。

Neo4j MCP

Neo4j MCP gives AI assistants and LLM-powered tools direct, structured access to your Neo4j graph database. By implementing the Model Context Protocol (MCP), it acts as a bridge between any MCP-compatible client, such as Claude, Cursor, or VS Code with MCP support, and your Neo4j instance.

Features

• Explore your graph schema - discover node labels, relationship types, and property keys
• Let AI reason on your data model without prior knowledge
• Run Cypher queries - execute, read, and write queries against your database in response to natural language prompts
• Inspect and analyze data - retrieve nodes, relationships, and paths to answer questions, generate summaries, or feed data to other workflows

Tools

• get-schema — introspect labels, relationship types, property keys
• read-cypher — execute read-only Cypher queries that do not modify database data, enforced via EXPLAIN and Neo4j’s query-type classification. Note: custom procedures or functions incorrectly classified as read-only by Neo4j may bypass this check; ensuring correct classification is the responsibility of the procedure/function maintainer.
• write-cypher — execute write Cypher queries (disabled if NEO4J_MCP_READ_ONLY=true)
• list-gds-procedures — list available GDS procedures

Installation

Install with PyPI:

pip install neo4j-mcp-server

For manual installation or using brew, please see MCP documentation -> Installation.

Server configuration (VSCode - STDIO)

Create / edit mcp.json:

{
  "servers": {
    "neo4j": {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "neo4j_mcp_server"],
      "env": {
        "NEO4J_MCP_URI": "bolt://localhost:7687",
        "NEO4J_MCP_USERNAME": "neo4j",
        "NEO4J_MCP_PASSWORD": "password",
        "NEO4J_MCP_DATABASE": "neo4j",
      }
    }
  }
}

See MCP documentation > Configuration for more details.

Links

• Documentation: The official Neo4j MCP documentation.
• Discord: The Neo4j discord channel.
• Contributing Guide: Contribution workflow, development environment, mocks and testing.

For issues and feedback, you can also create a GitHub issue with reproduction details (omit sensitive data).