Memory vs MCP Local Rag — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Memory vs MCP Local Rag
In-depth architectural comparison of the Memory and MCP Local Rag 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
Memory
Knowledge & Memory · Local stdio
Quality: 55/100 (Good) | Auth: No auth required
MCP Local Rag
Knowledge & Memory · Local stdio
Quality: 68/100 (Great) | Auth: No auth required
Verdict Summary: Choose Memory if you need specialized Knowledge & Memory tools running via a local process. Choose MCP Local Rag if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
M
Choose Memory when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Privacy-first document search server running entirely locally. Supports semantic search over PDFs, DOCX, TXT, and Markdown files with LanceDB vector storage and local embeddings - no API keys or cloud services required.
Flagship.** One call returns everything needed to understand this user for a query — relevant memories + profile + confirmed facts + behavioral inferences (plus counterfactual & cross-domain hints). Drop straight into any LLM's context.
zhiji_memory_search
Lighter, recall-only: the 11-stage hybrid pipeline (trigram FTS + semantic + time-decay), returns scored snippets with sources.
zhiji_profile_get
7-layer / 37-dim user profile as an inject-ready natural-language summary.
zhiji_facts_get
Structured atomic facts (subject attribution, confidence, conflict status) — for exact names/dates/counts, not narrative.
zhiji_prospective_due
Due/upcoming intentions (todos, promises, plans) within a time window — for proactively nudging the user.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Memory is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, MCP Local Rag belongs to Knowledge & Memory using local stdio subprocess. Select Memory when you need capabilities focused on knowledge & memory and MCP Local Rag when you require tools for knowledge & memory.
Write a conversation turn to long-term memory; async embedding + profile/fact extraction + importance scoring follow. **Text only.
zhiji_ingest_file
Multimodal ingest — audio / image / PDF / Word / Excel / video → Whisper transcribe / Tesseract OCR / doc parse → memory. Audio & video also get acoustic-emotion analysis.
zhiji_feedback
Thumbs up/down on the last recall/answer → feeds the self-evolution reward and reinforces (or penalizes) the Q-value of recently retrieved memories. The "gets better the more you use it" loop.
zhiji_status
Health & memory scale (files / chunks / FTS availability). Call first to verify connectivity.
MCP Local Rag Tools (9)
sync_start
Reconcile the index with all configured roots or one path
sync_status
Poll a running sync job
ingest_file
Ingest or replace one file
ingest_data
Ingest text, Markdown, or HTML already held by the client