In-depth architectural comparison of the Weighted Compact and Codebase Memory 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
Codebase Memory MCP
Knowledge & Memory · Local stdio
Quality: 72/100 (Great) | Auth: No auth required
Verdict Summary: Choose Weighted Compact if you need specialized Knowledge & Memory tools running via a local process. Choose Codebase Memory 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).
Code-intelligence engine that indexes a repo into a persistent knowledge graph — functions, classes, call chains, HTTP routes, cross-service links. 159 languages via tree-sitter + Hybrid LSP, sub-ms structural queries, 99% fewer tokens than grep. Single static binary, zero dependencies, 100% local. npx codebase-memory-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
Codebase Memory MCP Tools (14)
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, Codebase Memory MCP belongs to Knowledge & Memory using local stdio subprocess. Select Weighted Compact when you need capabilities focused on knowledge & memory and Codebase Memory MCP when you require tools for knowledge & memory.
Index a repository into the graph. Auto-sync keeps it fresh after that.
list_projects
List all indexed projects with node/edge counts.
delete_project
Remove a project and all its graph data.
index_status
Check indexing status of a project.
search_graph
Structural, BM25, and semantic search. Page structural rows with `offset`/`limit` and ranked semantic rows independently with `semantic_offset`/`semantic_limit`.
trace_path
BFS traversal — who calls a function and what it calls (alias: `trace_call_path`). Depth 1-5.
detect_changes
Map git diff to affected symbols + blast radius with risk classification.
query_graph
Execute Cypher-like graph queries (read-only).
get_graph_schema
Node/edge counts, relationship patterns, property definitions per label. Run this first.
get_code_snippet
Read source code for a function by qualified name.