NC

neo4j-contrib/mcp-aura-gds-standalone

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

5 stars 3 forks 质量 58 趋势 13

A collection of Model Context Protocol (MCP) servers that provide graph data science capabilities through Neo4j Graph Data Science (GDS).

概览

A collection of Model Context Protocol (MCP) servers that provide graph data science capabilities through Neo4j Graph Data Science (GDS). These servers enable AI agents to perform graph analytics workflows including loading graphs, running algorithms, and managing GDS sessions. Direct graph loading and analysis server. Load graphs programmatically via JSON data structures or Supabase queries, then run graph algorithms. - Load graphs directly from structured data (nodes/relationships as JSON) - Fetch graph data from Supabase databases - Run algorithms: PageRank, Betweenness, WCC, Leiden - Session and graph management File-based graph loading server. Load graphs from JSON files or fetch data from Supabase and save to files for later analysis. - Load graphs from JSON files - Fetch and persist graph data from Supabase - Run algorithms: PageRank, Betweenness, WCC, Leiden - Session and graph management Both servers require Neo4j Aura API credentials. Add to your claude_desktop_config.

README

🔍 Neo4j Aura GDS MCP Servers

A collection of Model Context Protocol (MCP) servers that provide graph data science capabilities through Neo4j Graph Data Science (GDS). These servers enable AI agents to perform graph analytics workflows including loading graphs, running algorithms, and managing GDS sessions.

📦 Available Servers

mcp-neo4j-aura-gds-standalone

Direct graph loading and analysis server. Load graphs programmatically via JSON data structures or Supabase queries, then run graph algorithms.

Key Features:

  • Load graphs directly from structured data (nodes/relationships as JSON)
  • Fetch graph data from Supabase databases
  • Run algorithms: PageRank, Betweenness, WCC, Leiden
  • Session and graph management

Install: uvx mcp-neo4j-aura-gds-standalone

mcp-neo4j-aura-gds-standalone-file

File-based graph loading server. Load graphs from JSON files or fetch data from Supabase and save to files for later analysis.

Key Features:

  • Load graphs from JSON files
  • Fetch and persist graph data from Supabase
  • Run algorithms: PageRank, Betweenness, WCC, Leiden
  • Session and graph management

Install: uvx mcp-neo4j-aura-gds-standalone-file

🚀 Quick Start

Both servers require Neo4j Aura API credentials. Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "neo4j-gds": {
      "command": "uvx",
      "args": ["mcp-neo4j-aura-gds-standalone"],
      "env": {
        "CLIENT_ID": "",
        "CLIENT_SECRET": "",
        "CLOUD_PROVIDER": "gcp",
        "CLOUD_REGION": "europe-west1"
      }
    }
  }
}

🔑 Authentication

Get Aura API credentials from Neo4j Aura Console:

  1. Navigate to account settings
  2. Create API credentials (Client ID and Client Secret)
  3. Optionally specify a Project ID to scope sessions

🛠️ Development

# Install uv
pip install uv

# Clone and setup
git clone https://github.com/neo4j-contrib/mcp-aura-gds-standalone.git
cd mcp-aura-gds-standalone
uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"

📄 License

MIT License - see LICENSE file for details.

在 GitHub 查看完整 README

安装

uvx mcp-neo4j-aura-gds-standalone
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "neo4j-gds": { "command": "uvx", "args": ["mcp-neo4j-aura-gds-standalone"], "env": { "CLIENT_ID": "<your-aura-client-id>", "CLIENT_SECRET": "<your-aura-client-secret>", "CLOUD_PROVIDER": "gcp", "CLOUD_REGION": "europe-west1" } } } }