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.
Privacy-first document search server running entirely locally. Supports semantic search over PDFs, DOCX, TXT, and Markdown files with LanceDB vector storage and local embeddings - no API keys or cloud services required.
Self-hosted semantic memory server, served over MCP, for an engineering team's tribal knowledge: the tacit decisions and hard-won reasoning behind the code, captured once and kept queryable for the team and the agents they work with. Postgres-backed (pgvector).
Quality signal
57/100 (Good)
52/100 (Fair)
Install path
npx · high
npx · high
Engagement
2 0 0 360
1 0 0 9
Tools
Runs fully locally with no external API or cloud dependencySupports semantic search combined with keyword boosting for exact matchesIndexes PDF, DOCX, Markdown, and plain text filesSemantic chunking preserves topic boundaries and code blocksMCP protocol support for integration with AI tools and CLI usageFile sync and incremental indexing with status and control tools
MCP server exposing semantic memory graphPostgres backend with pgvector for vector searchSupports local or cloud embedding and inference providersBootstrap and register projects with bearer token issuanceDiagnostic commands for configuration and provider readiness
