{"id":"cedricvidal-memorious-mcp","name":"memorious-mcp","homepage":null,"repo_url":"https://github.com/cedricvidal/memorious-mcp","category":"ai-ml","subcategories":[],"tags":["mcp","semantic-memory","chroma","local-first","python","fastmcp"],"what_it_does":"memorious-mcp is a local Model Context Protocol (MCP) server that provides semantic long-term memory operations—store, recall (vector similarity search), and forget—using ChromaDB for persistent on-disk storage.","use_cases":["Personal assistant memory (remember preferences and facts across sessions)","Project-/folder-scoped knowledge management for AI agents","Context preservation for local developer workflows","Semantic retrieval when queries don’t exactly match stored keys"],"not_for":["Storing highly sensitive data that would be unsafe unencrypted on disk","Environments needing centralized/networked memory services or managed hosting","Use cases requiring fine-grained access control across users"],"best_when":"You want local-only semantic memory for an MCP-capable assistant, with persistent storage and simple store/recall/forget tool semantics.","avoid_when":"You need encryption-at-rest, multi-tenant isolation, or authentication/authorization controls beyond local usage.","alternatives":["Any other MCP memory server using vector search","Local embedding + vector DB (e.g., ChromaDB) with a custom MCP wrapper","Exact-key local KV store approaches (no semantic search) paired with an MCP layer"],"af_score":58.0,"security_score":33.2,"reliability_score":23.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:33:32.520418+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No authentication/authorization is described. The intended usage is local stdio MCP transport, so access control is effectively limited to local machine access."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source / local execution; no hosted pricing mentioned."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":["Local machine only (no network calls claimed)"],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":58.0,"security_score":33.2,"reliability_score":23.8,"mcp_server_quality":72.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":5.0,"tls_enforcement":100.0,"auth_strength":5.0,"scope_granularity":0.0,"dependency_hygiene":60.0,"secret_handling":15.0,"security_notes":"The README claims local-only processing and warns that data is stored unencrypted on disk in the .memorious directory. No authentication/authorization model is described, so anyone with local access could read the stored memories. Memory/backups management should be treated as a security control.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":20.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":"No explicit idempotency or update semantics are documented for store/forget; repeated calls may create duplicates or re-delete depending on backend behavior.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Data is persisted to an unencrypted on-disk directory (.memorious by default), so agents should avoid storing secrets.","No auth is described; assume the MCP server is not safe for multi-user/shared environments.","Store/recall/forget are keyed around short canonical keys; poor key design can reduce recall quality."]}}