In-depth architectural comparison of the Weighted Compact 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
Weighted Compact
Knowledge & Memory · Local stdio
Quality: 41/100 (Fair) | Auth: No auth required
Scrivener MCP
Knowledge & Memory · Local stdio
Quality: 61/100 (Good) | Auth: No auth required
Verdict Summary: Choose Weighted Compact 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 Weighted Compact 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: Provably faithful recap with four invariants checked on all sessions, Local substrate of correction turns with multiple importance signals, Zero outbound network calls enforced by CI.
Inspectable memory substrate for Claude Code. Three read-only MCP tools (searchpairs, compactsession, substrateinfo) over a local-first, signal-scored parse of /.claude/projects/. Per-pair scores are numpy columns on disk, not opaque vectors in a service. Zero outbound calls (CI-enforced).
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
Tools & Capabilities Breakdown
Weighted Compact Tools (6)
Provably faithful recap with four invariants checked on all sessions
Local substrate of correction turns with multiple importance signals
Zero outbound network calls enforced by CI
Minimal idle RAM usage (0 MB between invocations)
MCP tools for searchpairs, compactsession, and substrateinfo
Compatibility with Python 3.11+ and stdlib-only recap mode
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).
Weighted Compact is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Scrivener MCP belongs to Knowledge & Memory using local stdio subprocess. Select Weighted Compact when you need capabilities focused on knowledge & memory and Scrivener MCP when you require tools for knowledge & memory.