sylweriusz/mcp-neo4j-memory-server
If you are the rightful owner of mcp-neo4j-memory-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol (MCP) server that provides AI assistants with persistent, intelligent memory capabilities using Neo4j's graph database with unified architecture.
Tools
Functions exposed to the LLM to take actions
memory_store
Create memories with observations and relationships. Pattern: Search→Create→Connect. Observations: Self-contained context units (what/when/where/why/impact). LocalIds: Cross-references within THIS request only. Limits: 50 memories, 200 relations. Quality: Each observation = complete detective notes answering setting/action/actors/evidence/impact/significance.
memory_find
Unified search/retrieval. Query: text, IDs array, or "*". Context: minimal (lists), full (everything), relations-only (graph). Temporal: createdAfter "7d"/"2024-01-15". Graph: traverseFrom + relations + depth. Always search before creating. Updates access timestamps for analytics.
memory_modify
Update/delete memories, manage observations/relations. Operations: update (properties), delete (cascade), add-observations (append insights), create-relations (link existing). Atomic: All succeed or all fail. Quality: One substantial observation per session - complete context stories, not fragments.
database_switch
Switch active database context (creates if missing). ALL subsequent operations use this DB. Call once per session/project. Like 'cd' for memories. Session-scoped: Establishes context for entire workflow, not per-operation.
Prompts
Interactive templates invoked by user choice
explore-memory-graph
null
create-project-knowledge
null
debug-orphaned-memories
null
document-decision
null
analyze-memory-quality
null
text-to-knowledge-graph
null
vibe-code-with-memory
null
refactor-with-rationale
null
evolve-architecture
null
Resources
Contextual data attached and managed by the client