In-depth architectural comparison of the Agent Memory and Scrivener MCP 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
Agent Memory
Knowledge & Memory · Local stdio
Quality: 47/100 (Fair) | Auth: No auth required
Scrivener MCP
Knowledge & Memory · Local stdio
Quality: 61/100 (Good) | Auth: No auth required
Verdict Summary: Choose Agent Memory if you need specialized Knowledge & Memory tools running via a local process. Choose Scrivener MCP 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 Agent 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).
Primary tools included: Three-layer memory: identity, active context, and archive, Semantic recall by meaning rather than keywords, Graph memory tracking updates, extensions, derivations, and expirations.
Three-layer memory system for agents (identity/active/archive) with semantic search, graph relationships, conflict detection, and LearningMachine. Built by an agent, for agents. No API keys required.
Connect Scrivener 3 writing projects to Claude and other AI assistants. 47 tools for document management, writing analysis, semantic search, character/plot memory, and content enhancement. Progressive skill loading, relationship engine with HMS triplets, and JS fallback for offline semantic search. npm i -g scrivener-mcp
Category & Scope
Tools & Capabilities Breakdown
Agent Memory Tools (6)
Three-layer memory: identity, active context, and archive
Semantic recall by meaning rather than keywords
Graph memory tracking updates, extensions, derivations, and expirations
Auto-capture of decisions and insights without explicit commands
LearningMachine for tracking recall hits, misses, and corrections
Local SQLite storage with no cloud or API key dependencies
Scrivener MCP Tools (6)
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).
Agent Memory is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Scrivener MCP belongs to Knowledge & Memory using local stdio subprocess. Select Agent Memory when you need capabilities focused on knowledge & memory and Scrivener MCP when you require tools for knowledge & memory.