Academic-paper knowledge-base MCP server: PDF ingestion (MinerU), Qdrant vector search with reranking, two-phase KB management
View on GitHub ↗Status: preview release (v0.1.0). Interfaces and storage layout may change in future versions.
scholar-rag-mcp is a publishable academic-paper knowledge-base MCP tool. Point it at a folder of PDFs and it ingests each paper through a real parsing pipeline (MinerU), normalizes metadata, annotates section structure, chunks and embeds the text, and stores everything in Qdrant - after which an agent (or you) can semantically search chunks, run PubMed-style document queries, read full text section by section, add/remove single papers, and manage knowledge bases - all through 11 MCP tools over stdio. Embedding, annotation and re-ranking run on OpenAI-compatible model services (vLLM) with in-process fallbacks.
- Real ingestion pipeline: MinerU PDF parsing (python/cli/api backends) - metadata extraction (local heuristics, CrossRef, optional GROBID) - cleaning - section annotation - deterministic chunking (configurable 300/1500/100 chars) - embedding. - Fast retrieval at scale: embedding first-pass + cross-encoder re-rank, optional metadata filtering (docid, section, year, journal, ...) evaluated inside the Qdrant index. 100k-chunk p95 query latency ") to actually delete the Qdrant collection, kb directory and its job history.
For known limitations and upgrade guidance see docs/handoffs/release-notes-v0.1.0.md.
- Qdrant is pinned to v1.12.5 - it is the highest version that runs on glibc 2.35; auto-launch downloads it on first use. On glibc = 2.38 you may run a newer version, but the data format is not forward-compatible with older kbs in this release. - MinerU runs in its own pix
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/notwhiteblank--scholar-rag-mcp.html)
An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
sosoj92/jarvis-assistant-vocalAssistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.
Stupidoodle/swissdevjobs-cliSearch & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency Python CLI + MCP server + Claude Code plugin
agents-universe/agents-universe让智能体像人一样学习和工作，共享智能体和项目记忆
bybit-exchange/kaasTurn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.
alxgntv/substack-api-mcpMCP server for Substack posts (FastMCP + substack-api-client)
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.