Marketplace for trusted AI agent skills

Query Neo4j graph data from agent workflows through MCP

Skill Detail

Query Neo4j graph data from agent workflows through MCP

Connect MCP-compatible agents to Neo4j so they can inspect graph schemas, run Cypher queries, manage graph memory, and operate Aura instances from chat.

Data Extraction & TransformationMCP
Data Extraction & Transformation MCP Security Reviewed
⭐ 947 GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill query-neo4j-graph-data-from-agent-workflows-through-mcp Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
View source Documentation
At a glance
Tools required
Neo4j database or Aura account, APOC for schema inspection, Python package or uvx, MCP-compatible client
Install & setup
Install the needed server package such as `pip install mcp-neo4j-memory` or run it with `uvx mcp-neo4j-memory@0.4.5`, then add the server command and Neo4j URL, username, and password to the MCP client configuration.
Author
Neo4j Labs
Publisher
Organization
Last updated
May 20, 2026
Quick brief

Use the Neo4j MCP servers when an agent needs controlled access to graph data or persistent graph memory. The operator chooses the Cypher, memory, Aura API, or data-modeling server, configures Neo4j credentials and transport, then exposes the tools to an MCP client such as Claude Desktop, Cursor, VS Code, Windsurf, or Gemini CLI. Invoke this for Text2Cypher, graph exploration, graph-backed memory, and Neo4j Aura operations; keep the scope to MCP-mediated Neo4j workflows, not general database administration.

How it works

What this skill actually does

Inputs and prerequisites: Neo4j database or Aura account, APOC for schema inspection, Python package or uvx, MCP-compatible client.

Setup notes: Install the needed server package such as `pip install mcp-neo4j-memory` or run it with `uvx mcp-neo4j-memory@0.4.5`, then add the server command and Neo4j URL, username, and password to the MCP client configuration.

Source and verification boundary: use https://neo4j.com/developer/genai-ecosystem/model-context-protocol-mcp/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.