Paperlib MCP is an academic literature management system that enables PDF import, intelligent search, knowledge graph construction, and automated literature review generation.

Document Management & Processing: Import PDFs with automatic text extraction, chunking, and vector embedding generation. List, retrieve, update metadata, delete, re-chunk, and regenerate embeddings for documents. Monitor ingestion status and troubleshoot errors.

Search & Retrieval: Perform hybrid searches combining full-text (FTS) and semantic vector search with configurable weighting, or use FTS-only/vector-only modes. Retrieve specific chunks, explain search results with detailed breakdowns, and build reusable evidence packs for research queries.

Knowledge Graph Construction: Extract entities (topics, methods, measures, identification strategies), relationships, and claims using LLM-driven analysis. Canonicalize and merge duplicate entities, lock entities to prevent auto-merging, and build topic communities using the Leiden clustering algorithm for macro/micro analysis. Group and cluster similar claims across papers.

Literature Review Generation: Generate structured review outlines with deterministic, reproducible templates. Draft complete literature reviews or specific sections (methodology, findings, gaps) based on topics or evidence packs. Build section-specific evidence packs, validate citation compliance, and export evidence matrices (paper-level and claim-level) in JSON/CSV formats.

Data Export & Analysis: Export compact relation views, grouped claim matrices with representative claims, section packets with complete writing inputs, and full markdown templates with placeholders for composition.

System Management: Perform health checks for database, S3/MinIO storage, and GraphRAG layer. Execute batch operations (bulk graph extraction, community rebuilds, parallel summarization), clear graph data selectively or globally, manage taxonomy rules for controlled vocabulary, and pre-calculate document frequency and topic features for performance optimization.

Provides S3-compatible object storage for PDF documents and related files in the academic literature management system.

Stores document metadata, vector embeddings, knowledge graph entities and relations, and supports hybrid search combining full-text search with pgvector semantic search.