medxpert-library-connector
Related Servers
Alternatives to medxpert-library-connector
No user-submitted related servers found.
Related Servers
- FlicenseAqualityDmaintenanceEnables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.4-
- FlicenseAqualityDmaintenanceEnables retrieval-augmented question answering over Obsidian vaults and document folders, with local embeddings, vector search, and cited source paths.7-
- AlicenseNot gradedqualityDmaintenanceEnables querying a local health knowledge base with hybrid RAG (vector + FTS5) and exploring backlinks between notes.MIT
- AlicenseAqualityCmaintenanceEnables an LLM to autonomously maintain a Markdown-based wiki with YAML frontmatter, using hybrid BM25 and local CPU vector search for fully offline retrieval without external APIs or databases.1831 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables LLM agents to ingest Markdown and text into a local SQLite-backed vector knowledge base, run semantic similarity searches, and retrieve evidence or optionally generate grounded answers to questions. Embeddings come from sentence transformers with optional OpenAI-based answer generation.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to run semantic search over local Obsidian or Markdown vaults, returning notes ranked by meaning with paths, headings, scores, and snippets, and to trigger incremental reindexing of changed notes. Everything runs on the user's own machine, so no note content leaves it.MIT
TDQS
Scored across 4 tools
get_page and list_sources are clearly distinct (full-text read vs. collection metadata), but search_knowledge and ask_knowledge both retrieve from the same knowledge base and could be confused—one returns raw snippets, the other a generated answer with citations. The descriptions do disambiguate them adequately, but the boundary requires reading.
All four tools follow a clean verb_noun snake_case pattern: search_knowledge, get_page, list_sources, ask_knowledge. No mixed conventions or vague verbs.
Four tools is well-scoped for a read-only local wiki/RAG connector: search, fetch, enumerate sources, and answer. Each tool earns its place with no redundancy.
Covers the core read-only lifecycle (discover scope, search, read page, ask). A notable gap is the absence of a list/browse-pages operation—list_sources only returns counts and directories, so enumerating actual pages depends on search results or known filenames.