# MCP Neo4j Memory Ops

> Use Neo4j memory MCP for creating/updating linked memories (entities, relations), de-duplication (DRY), and retrieval queries for project continuity. Use when saving global learnings or querying graph relationships.

- Skill: `janjaszczak/mcp-neo4j-memory-ops` (Agent Skill)
- Install (CLI): `npx skillmds@latest add janjaszczak/mcp-neo4j-memory-ops`
- Raw SKILL.md: https://api.skillmd.com/api/skills/janjaszczak/mcp-neo4j-memory-ops/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: janjaszczak (https://skillmd.com/u/janjaszczak)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/janjaszczak/mcp-neo4j-memory-ops

---


# mcp-neo4j-memory-ops

## When to use (beyond recall)
- User requests “zapisz do pamięci” / “zaktualizuj wspomnienia”.
- Need relationship-aware retrieval: “jak to się łączy z X”, “co już robiliśmy podobnego”.

## Procedure
1. Retrieve candidate existing nodes (fuzzy match).
2. Merge if similar; avoid duplicates.
3. Add explicit relations:
   - PROJECT → DECISION
   - DECISION → CONSTRAINT
   - TOOL → WORKFLOW
4. Store “confidence” and “last_updated”.

## Output
- What nodes/edges changed + short rationale.