
一个用于使用 MCP 进行端到端 Neo4j 开发的模板仓库
概览
一个用于使用MCP服务器进行端到端Neo4j图开发的模板。兼容 、 、 和 。 1. 提示输入您的 Neo4j 凭证和 OpenAI API 密钥 2.在配置中编写 .env 文件 3.为本地 MCP 服务器安装依赖 4.为所有 7 个工具生成 MCP 配置文件:- .mcp.json — Claude Code - .cursor/mcp.json — Cursor - .gemini/settings.json — Gemini CLI - .vscode/mcp.json — GitHub Copilot(VS Code)- opencode.json — OpenCode - .codex/config.toml — OpenAI Codex CLI - .vibe/config.toml — Mistral Vibe 如果你使用(不是上述7个编码工具之一),请将工作区安装为桌面扩展——无需git克隆。 1. — 必须安装后才能启动扩展(见下文“安装UV”) 2. — 工作区使用(块,实体)和(提取模式)。有两种选项: 每个Aura实例有一个名为neo4j的单一数据库——你不能创建额外的数据库。使用两个独立实例。 3.
概述(AI 翻译)
一个基于MCP服务器的端到端Neo4j图开发模板。兼容Claude代码、Cursor、Gemini CLI、GitHub Copilot(VS Code)、OpenCode、OpenAI Codex CLI和Mistral Vibe。
快速启动
然后打开你的AI编码工具:
| 工具 | 命令/动作 | 验证 |
|---|---|---|
| 克劳德代码 | claude |
/setup-workspace |
| 光标 | 在光标中打开此文件夹 | 让AI呼叫list_example_data_models |
| 双子座CLI | gemini |
让双子座打电话给list_example_data_models |
| GitHub Copilot VS Code | 在VS Code中打开文件夹,使用代理模式 | 让Copilot呼叫list_example_data_models |
| 开放代码 | opencode |
请求呼叫list_example_data_models |
| Codex CLI | codex |
让Codex呼叫list_example_data_models |
| 密斯特拉尔维布 | vibe(提示时信任文件夹) |
让维布打电话给list_example_data_models |
setup.sh 将:
- 提示输入你的 Neo4j 凭证和 OpenAI API 密钥
- 用你的配置写入
.env。 - 为本地MCP服务器安装依赖
- 生成所有7个工具的MCP配置文件:
.mcp.json— 克劳德代码- '.Cursor/MCP。
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。
neo4j-mcp-workspace-template
A template for end-to-end Neo4j graph development using MCP servers. Compatible with Claude Code, Cursor, Gemini CLI, GitHub Copilot (VS Code), OpenCode, OpenAI Codex CLI, and Mistral Vibe.
Quick Start
git clone https://github.com/neo4j-field/neo4j-mcp-workspace-template
cd neo4j-mcp-workspace-template
chmod +x setup.sh && ./setup.sh
Then open your AI coding tool:
| Tool | Command / action | Verify |
|---|---|---|
| Claude Code | claude |
/setup-workspace |
| Cursor | Open this folder in Cursor | Ask AI to call list_example_data_models |
| Gemini CLI | gemini |
Ask Gemini to call list_example_data_models |
| GitHub Copilot VS Code | Open folder in VS Code, use Agent mode | Ask Copilot to call list_example_data_models |
| OpenCode | opencode |
Ask to call list_example_data_models |
| Codex CLI | codex |
Ask Codex to call list_example_data_models |
| Mistral Vibe | vibe (trust the folder when prompted) |
Ask Vibe to call list_example_data_models |
setup.sh will:
- Prompt for your Neo4j credentials and OpenAI API key
- Write
.envwith your configuration - Install dependencies for the local MCP servers
- Generate MCP config files for all 7 tools:
.mcp.json— Claude Code.cursor/mcp.json— Cursor.gemini/settings.json— Gemini CLI.vscode/mcp.json— GitHub Copilot (VS Code)opencode.json— OpenCode.codex/config.toml— OpenAI Codex CLI.vibe/config.toml— Mistral Vibe
Claude Desktop
If you use Claude Desktop (not one of the 7 coding tools above), install the workspace as a Desktop Extension — no git clone needed.
Prerequisites
-
uv — must be installed before the extension can start (see Installing uv below)
-
Two Neo4j databases — the workspace uses a Documents DB (chunks, entities) and an Ontology DB (extraction schema). Two options:
Option How Two Aura instances Create two free AuraDB instances — one for documents, one for the ontology. Each has its own URI, username, and password. Neo4j Desktop (local) Install Neo4j Desktop, create one DBMS, then add two databases inside it (e.g. neo4jandontology). Both share the same URI and credentials.Aura free tier note: each Aura instance has a single database named
neo4j— you cannot create additional databases. Use two separate instances. -
An OpenAI API key — for embeddings and entity extraction (or configure another provider via Extra Environment Variables in the install dialog)
Install
- Download
neo4j-mcp-workspace.dxtfrom the latest release
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add neo4j-field/neo4j-mcp-workspace-template