Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
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
Generate and read PDFs for AI agents: a generatepdf tool (HTML, a URL, or a template + JSON → PDF) and a readpdf tool (a PDF → text/markdown). Run locally with npx @docweave/mcp or use the hosted streamable-HTTP endpoint. Chromium-rendered, priced per document.
Quality signal
55/100 (Good)
49/100 (Fair)
Install path
uvx · high
npx · high
Engagement
4 1 1 38,052
0 0 0 0
Tools
Indexes 158 languages via tree-sitter and Hybrid LSPPersistent knowledge graph of code elements and relationsSingle static binary with zero runtime dependenciesSub-millisecond structural queries using CypherBuilt-in 3D graph visualization UI (optional)15 MCP tools including search, trace, architecture analysis
