In-depth architectural comparison of the Central Intelligence and Engram Rs 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
Central Intelligence
Knowledge & Memory · Local stdio
Quality: 49/100 (Fair) | Auth: API Key required
Engram Rs
Knowledge & Memory · Local stdio
Quality: 57/100 (Good) | Auth: API Key required
Verdict Summary: Choose Central Intelligence if you need specialized Knowledge & Memory tools running via a local process. Choose Engram Rs 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?
Choose Central Intelligence when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Freemium).
You have access to required keys: CI_API_KEY.
Primary tools included: Five MCP tools: remember, recall, context, forget, share, Semantic search via vector embeddings, Agent, user, and organization scoped memory.
Persistent memory for AI agents. Five tools (remember, recall, context, forget, share) with semantic search via vector embeddings and agent/user/org scoping. Works with Claude Code, Cursor, Windsurf, and any MCP client.
Hierarchical memory engine for AI agents with automatic decay, promotion, semantic dedup, and self-organizing topic tree. Single Rust binary, zero external dependencies.
Category & Scope
Tools & Capabilities Breakdown
Central Intelligence Tools (6)
Five MCP tools: remember, recall, context, forget, share
Semantic search via vector embeddings
Agent, user, and organization scoped memory
Verbatim memory retrieval without rewriting
Cross-tool memory integration with AI coding platforms
Open-source with Apache 2.0 license
Engram Rs Tools (16)
engram_store
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).
Central Intelligence is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Engram Rs belongs to Knowledge & Memory using local stdio subprocess. Select Central Intelligence when you need capabilities focused on knowledge & memory and Engram Rs when you require tools for knowledge & memory.
Store a memory. All memories start in Buffer and promote to Working/Core through access frequency and LLM quality gating. Procedural memories and lessons (tag=lesson) auto-promote to Working after 2h. Use supersedes to replace outdated memories by their ids.
engram_recall
Hybrid semantic + keyword search with budget-aware retrieval. Fast by default (~30ms cached, ~1s first query). Optional expand adds LLM query expansion (+1-2s) — only use for short/vague queries.
engram_recent
List recent memories by creation time. Good for session context recovery.
engram_resume
Full memory bootstrap for session recovery. Returns core (permanent knowledge), working (ongoing context/decisions), buffer (transient), recent activity, and session notes. Use workspace tags to filter by current work context. Compact mode (default) minimizes token usage.
engram_extract
Extract structured memories from raw text using LLM. Feed conversation logs or notes and get individual memories.
engram_search
Quick keyword search. Lighter than recall — no scoring or budget logic.
engram_consolidate
Run a memory consolidation cycle. Promotes important memories upward, drops decayed entries. With merge=true, uses LLM to merge similar memories.
engram_stats
Get memory statistics: counts per layer, AI status, version.
engram_repair
Repair FTS search index. Removes orphaned entries and rebuilds missing ones. Safe to run anytime — idempotent.
engram_health
Detailed health check: uptime, RSS memory, embed cache stats, AI config status.
engram_triggers
Fetch trigger memories for a specific action. Call before performing an action (e.g. git-push, deploy) to recall relevant lessons and rules.
engram_delete
Delete a memory by ID. Use when a memory is outdated, incorrect, or redundant.