{"id":"elvismdev-mem0-mcp-selfhosted","name":"mem0-mcp-selfhosted","af_score":64.5,"security_score":47.8,"reliability_score":37.5,"what_it_does":"Provides a self-hosted MCP server exposing mem0 memory-management tools (and optional Neo4j graph tools) for use with Claude Code, backed by Qdrant for vector search, Ollama for embeddings and optionally LLM, and optional Anthropic/OAT integration for LLM-based extraction.","best_when":"You want self-hosted AI memory with Claude Code using MCP/stdio, and you can run Qdrant + Ollama (and optionally Neo4j).","avoid_when":"You need strict, centrally managed security/compliance controls without handling tokens/models locally; or you cannot provide/secure Anthropic or Ollama dependencies.","last_evaluated":"2026-03-30T15:20:26.367390+00:00","has_mcp":true,"has_api":false,"auth_methods":["Claude Code OAT token auto-read from ~/.claude/.credentials.json (zero-config for Claude Code)","MEM0_ANTHROPIC_TOKEN env var to supply OAT/API token","ANTHROPIC_API_KEY env var for non-Claude-Code deployments"],"has_free_tier":false,"known_gotchas":["Graph tooling (Neo4j + graph LLM steps) may increase latency; hooks explicitly disable graph to stay within timeout budgets.","Some configuration defaults assume local services (Qdrant localhost:6333, Ollama localhost:11434).","If Ollama embedding model dimensions or Qdrant collection configuration mismatch (MEM0_EMBED_DIMS), operations may fail."],"error_quality":0.0}