In-depth architectural comparison of the MCP Memory Graph and Context Keeper 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
MCP Memory Graph
Knowledge & Memory · Local stdio
Quality: 45/100 (Fair) | Auth: No auth required
Context Keeper
Knowledge & Memory · Remote HTTP/SSE
Quality: 51/100 (Good) | Auth: No auth required
Verdict Summary: Choose MCP Memory Graph if you need specialized Knowledge & Memory tools running via a local process. Choose Context Keeper if your workspace requires Knowledge & Memory integration with remote web transport. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose MCP Memory Graph when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Freemium).
Primary tools included: SQLite-based persistent local memory, Hybrid semantic and keyword search, Knowledge graph for linked entities and memories.
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
LLM-driven context and memory management with wide-recall + precise-reranking RAG architecture. Features multi-dimensional retrieval (vector/timeline/knowledge graph), short/long-term memory, and complete MCP support (HTTP/WebSocket/SSE).
MCP Memory Graph is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Context Keeper belongs to Knowledge & Memory using remote streaming HTTP/SSE transport. Select MCP Memory Graph when you need capabilities focused on knowledge & memory and Context Keeper when you require tools for knowledge & memory.