{"id":"coleam00-mcp-mem0","name":"mcp-mem0","af_score":51.2,"security_score":36.5,"reliability_score":30.0,"what_it_does":"Provides an MCP server template integrated with Mem0 to let AI agents save, retrieve, and semantically search long-term memories backed by Supabase/PostgreSQL (vector storage) and configurable via an LLM provider for embeddings.","best_when":"You control the deployment (stdio or SSE) and can configure the LLM provider and PostgreSQL/Supabase for embeddings and storage.","avoid_when":"You need a multi-tenant, internet-exposed service with robust authentication/authorization and documented security guarantees.","last_evaluated":"2026-03-30T13:26:04.416887+00:00","has_mcp":true,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["If using SSE transport, ensure the client URL/path matches the server’s expected MCP SSE endpoint (README uses /sse in examples).","Embedding/LLM provider configuration is required for semantic indexing; misconfiguration will likely prevent memory operations but retry/error guidance is not documented.","No mention of server-side auth: do not expose SSE publicly without compensating controls (network/VPC/firewall)."],"error_quality":0.0}