MCPgee
MCPgee
MCPgeeMCPgee

Neo4j GDS

v1.0.0•Data Science & ML•stable

MCP Server with tools from Neo4j GDS(Graph Data Science) library.

gds-agentmcpai-integration
Share:
86
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Neo4j GDS?

Neo4j GDS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server with tools from neo4j gds(graph data science) library.

MCP Server with tools from Neo4j GDS(Graph Data Science) library.

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP Server with tools from Neo4j GDS(Graph Data Science) lib

Use Cases

Execute Neo4j Graph Data Science algorithms through Claude.
Perform graph analysis and machine learning on connected data.
Query and analyze knowledge graphs.
neo4j-contrib

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 11, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx gds-agent

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Neo4j GDS

The GDS Agent MCP server exposes Neo4j Graph Data Science library algorithms and graph operations to AI assistants through the Model Context Protocol. It connects to a local or cloud Neo4j instance (including Aura) and lets you run graph algorithms like shortest path, community detection, and centrality measures by simply asking questions about your graph data in natural language. Data scientists and engineers use it to explore knowledge graphs, run GDS pipelines, and analyze connected data without writing Cypher queries manually.

Prerequisites

  • Python 3.10 or later with uv installed
  • A running Neo4j instance (local or Aura) with the Graph Data Science plugin enabled
  • Neo4j connection credentials: URI, username, and password
  • An MCP-compatible client such as Claude Desktop
  • For Aura cloud sessions: AURA_API_CLIENT_ID and AURA_API_CLIENT_SECRET
1

Ensure Neo4j GDS is installed and running

Verify that your Neo4j instance has the Graph Data Science plugin installed and that it is accessible from the machine running the MCP server. For Aura, confirm your project has GDS sessions enabled.

2

Install uv and verify the gds-agent package

The gds-agent is distributed via PyPI and run with uvx. Find the path to uvx for use in the MCP config.

# Install uv if not already present:
curl -LsSf https://astral.sh/uv/install.sh | sh

# Verify uvx:
which uvx
uvx gds-agent --help
3

Configure your MCP client with Neo4j credentials

Add gds-agent to your Claude Desktop MCP configuration with the required Neo4j environment variables. Replace the credential placeholders with your actual values.

4

Connect Claude to your graph and start querying

Ask Claude a graph question. The server will select appropriate GDS algorithms (e.g., shortest path, PageRank, Louvain community detection) and execute them against your Neo4j database.

5

Manage Aura GDS sessions (cloud only)

For Neo4j Aura users, set the Aura API credentials and optional session parameters to allow the agent to create and manage GDS sessions automatically.

Neo4j GDS Examples

Client configuration

Add gds-agent to Claude Desktop with the Neo4j connection environment variables. Use the full uvx path from 'which uvx'.

{
  "mcpServers": {
    "neo4j-gds": {
      "command": "/opt/homebrew/bin/uvx",
      "args": ["gds-agent"],
      "env": {
        "NEO4J_URI": "bolt://localhost:7687",
        "NEO4J_USERNAME": "neo4j",
        "NEO4J_PASSWORD": "your_password",
        "NEO4J_DATABASE": "neo4j"
      }
    }
  }
}

Prompts to try

Example natural language prompts that trigger GDS algorithms on your graph data.

- "Find the shortest path between node A and node B in my graph"
- "Which nodes have the highest PageRank in the network?"
- "Run community detection on the graph and tell me how many clusters you find"
- "List all active GDS sessions and their memory usage"
- "What are the top 10 most connected nodes by degree centrality?"

Troubleshooting Neo4j GDS

Connection refused error when starting the server

Verify that Neo4j is running and accessible at the URI specified in NEO4J_URI. Test the connection with 'cypher-shell -u neo4j -p your_password' or the Neo4j Browser. For Aura, check that the instance is not paused.

GDS algorithm fails with 'procedure not found' error

Confirm the Graph Data Science plugin is installed in your Neo4j instance. In Neo4j Browser, run 'CALL gds.list()' — if this fails, the GDS plugin is not installed or not enabled for your edition.

Aura session creation fails with authentication error

Ensure AURA_API_CLIENT_ID and AURA_API_CLIENT_SECRET are set correctly. These are separate from your Neo4j database credentials — they are OAuth client credentials from the Aura Console API access settings.

Frequently Asked Questions about Neo4j GDS

What is Neo4j GDS?

Neo4j GDS is a Model Context Protocol (MCP) server that mcp server with tools from neo4j gds(graph data science) library. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Neo4j GDS?

Follow the installation instructions on the Neo4j GDS GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Neo4j GDS?

Neo4j GDS works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Neo4j GDS free to use?

Yes, Neo4j GDS is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Neo4j GDS Alternatives — Similar Data Science & ML Servers

Looking for alternatives to Neo4j GDS? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

{ "mcpServers": { "gds-agent": { "command": "npx", "args": ["-y", "gds-agent"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Neo4j GDS?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides