Use when installing, configuring, or troubleshooting the official Neo4j MCP server (neo4j/mcp): connecting Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, Kiro, or other MCP-compatible editors to a Neo4j database via stdio or HTTP transport. Covers the four MCP tools (get-schema, read-cypher, write-cypher, list-gds-procedures), read-only mode, and multi-database configuration. Does NOT cover writing Cypher queries via those tools — use neo4j-cypher-skill. Does NOT cover agent memory — use neo4j-agent-memory-skill. Does NOT cover Aura instance provisioning — use neo4j-aura-provisioning-skill.
92
88%
Does it follow best practices?
Impact
100%
1.33xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
VS Code MCP configuration
VS Code top-level key
100%
100%
stdio type field
100%
100%
Absolute path in command
0%
100%
Correct config file location
100%
100%
bolt:// URI scheme
100%
100%
NEO4J_DATABASE specified
100%
100%
Read-only flag set
37%
100%
Smoke test uses read-cypher
100%
100%
JSON validation step
100%
100%
Editor restart mentioned
100%
100%
Credentials not hardcoded in guide
100%
100%
HTTP transport shared server
HTTP transport flag
60%
100%
Port 8080
62%
100%
Bind address for team access
100%
100%
Security caveat documented
100%
100%
Credentials baked into server command
70%
100%
Editor config uses type:http
0%
100%
Editor config uses url field
100%
100%
No credentials in editor config
100%
100%
cursor_mcp.json uses mcpServers key
100%
100%
Per-request auth explanation
20%
100%
NEO4J_DATABASE specified
75%
100%
Claude Code Aura read-only setup
Existing config preserved
100%
100%
neo4j+s:// URI scheme
100%
100%
Absolute path for command
0%
100%
NEO4J_READ_ONLY set to true
50%
100%
NEO4J_DATABASE specified
75%
100%
Credentials in .env
100%
100%
.env gitignore note
100%
100%
write-cypher hidden in read-only
70%
100%
Toggle instructions
100%
100%
Smoke test uses read-cypher
25%
100%
mcpServers key used
100%
100%
66ed0e1
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.