In-depth architectural comparison of the Mem0 MCP Selfhosted and Genesys Memory MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Mem0 MCP Selfhosted
Knowledge & Memory · Local stdio
Quality: 57/100 (Good) | Auth: other
Genesys Memory
Knowledge & Memory · Local stdio
Quality: 56/100 (Good) | Auth: No auth required
Verdict Summary: Choose Mem0 MCP Selfhosted if you need specialized Knowledge & Memory tools running via a local process. Choose Genesys Memory if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Mem0 MCP Selfhosted when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: other (Free / Open Source).
Self-hosted mem0 MCP server for Claude Code with Qdrant vector search, Neo4j knowledge graph, and Ollama embeddings. Zero-config OAT auth, split-model graph routing, session hooks for automatic cross-session memory, and 11 tools. Supports both Anthropic and fully local Ollama setups.
Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).
Mem0 MCP Selfhosted is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Genesys Memory belongs to Knowledge & Memory using local stdio subprocess. Select Mem0 MCP Selfhosted when you need capabilities focused on knowledge & memory and Genesys Memory when you require tools for knowledge & memory.
List users/agents/runs with memory counts. Uses Qdrant Facet API.
delete_entities
Cascade-delete an entity and all its memories.
search_graph
Search Neo4j entities by name substring. Returns entities + outgoing relationships.
get_entity
Get all relationships for an entity (bidirectional: incoming + outgoing).
Genesys Memory Tools (13)
memory_store
Store a new memory. Use `related` for writer-specified **typed** edges (`{id, type}`); `related_to` is legacy and always creates `caused_by`. Optional `category`. May return `possible_conflicts` (heuristic hints).
memory_amend
Record a correction: creates a new memory that **supersedes** an existing one. The old memory is kept (decayed in recall), not deleted.
memory_recall
Recall memories by natural language query (vector + keyword + graph spreading activation). Supports `verbosity: "concise"` for lightweight payloads.
memory_search
Filtered vector search by status, category, date (`since`), last-active date (`active_since`), or entity. Pass an **empty query** to enumerate by recency instead (no embedder needed) — with `since`/`active_since` this answers "what's new since I last looked" without knowing what to query for.
memory_traverse
Walk the causal graph from a node. Returns reachable **nodes and the edges** of the induced subgraph (`source/target/type/weight/created_by`) — a superset of the BFS tree, so paths can be reconstructed. Honors `edge_types`.
memory_explain
Explain a memory's score. Includes a `score_model` block (formula + live per-force breakdown + staleness note) and `removal_impact`.
memory_stats
Get memory system statistics
pin_memory
Pin a memory so it's never forgotten
unpin_memory
Unpin a previously pinned memory
delete_memory
Permanently delete a memory
list_core_memories
List core memories, optionally filtered by category