MCP Memory Keeper
MCP Memory Keeper server providing persistent agent memory via SQLite — storing and retrieving memories with tags and categories, searching memories by content, managing memory collections, and integrating persistent knowledge storage into agent workflows that need to remember facts, decisions, and context across conversations.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Local SQLite. No network. OS file permissions. No secrets needed. Protect DB file if memories are sensitive.
⚡ Reliability
Best When
An agent needs simple persistent memory with SQLite backend — tag-based memory storage for local agent workflows requiring cross-session fact retention without vector database complexity.
Avoid When
You need semantic/vector search, multi-user memory, or high-throughput concurrent writes — use Weaviate or Eion instead.
Use Cases
- • Storing agent observations and learned facts from AI assistant agents
- • Retrieving relevant memories by search query from context-aware agents
- • Managing tagged memory collections from personal assistant agents
- • Persisting user preferences and interaction history from personalization agents
- • Building knowledge bases that grow over time from continuous learning agents
- • Enabling cross-session continuity from long-running assistant agents
Not For
- • High-performance semantic search (use vector DBs like Weaviate for embeddings)
- • Multi-user shared memory systems (SQLite is single-writer)
- • Production-scale deployments requiring ACID guarantees beyond SQLite
Interface
Authentication
No authentication — local SQLite database. Access controlled by OS file permissions on the SQLite database file.
Pricing
Free and open source. Local SQLite database — no cloud costs. Self-hosted.
Agent Metadata
Known Gotchas
- ⚠ SQLite is single-writer — concurrent agents may experience write contention
- ⚠ Memory search is keyword-based, not semantic — no vector similarity
- ⚠ Database file location must be configured correctly at startup
- ⚠ Community MCP from individual contributor — limited long-term maintenance guarantee
- ⚠ No built-in memory expiration or cleanup — database may grow unbounded
- ⚠ Tags and categories require consistent naming conventions for reliable retrieval
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for MCP Memory Keeper.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-07.