Paperlib MCP
Enables academic literature management through PDF import, hybrid search, knowledge graph construction, and automated literature review generation. Combines full-text search with semantic vector search for comprehensive paper analysis.
README
Paperlib MCP
Academic literature management and retrieval MCP server - supporting PDF import, hybrid search, knowledge graph construction, and literature review generation.
β¨ Features
| Feature | Description |
|---|---|
| PDF Import | Auto-extract text, chunk by page, generate vector embeddings |
| Hybrid Search | FTS full-text search + pgvector semantic search |
| Knowledge Graph | LLM-driven entity/relation/claim extraction, Leiden community detection |
| Review Generation | Structured literature review auto-generation based on evidence packs |
π Prerequisites
- PostgreSQL 16+ with pgvector extension
- MinIO or S3-compatible storage
- OpenRouter API Key
π Installation & Usage
Method 1: Docker Compose (Recommended for Beginners)
One-click launch of complete environment (PostgreSQL + MinIO + MCP):
git clone https://github.com/your-org/paperlib-mcp.git
cd paperlib-mcp
# Configure API Key
cp .env.example .env
# Edit .env and fill in OPENROUTER_API_KEY
# Start services
docker-compose up -d
Configure in Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"paperlib-docker": {
"command": "docker",
"args": [
"exec",
"-i",
"paperlib-mcp",
"python",
"-m",
"paperlib_mcp.server"
]
}
}
}
Method 2: uvx Install (Recommended)
Prerequisites: Requires available PostgreSQL (with pgvector) and MinIO/S3-compatible storage service.
<details> <summary>π‘ Quick Start Local Services (Optional)</summary>
docker-compose up -d postgres minio minio-init
</details>
Configure in Cursor/Claude Desktop, modify environment variables according to your actual service addresses:
{
"mcpServers": {
"paperlib": {
"command": "uvx",
"args": ["paperlib-mcp"],
"env": {
"POSTGRES_HOST": "localhost",
"POSTGRES_USER": "paper",
"POSTGRES_PASSWORD": "paper",
"POSTGRES_DB": "paperlib",
"S3_ENDPOINT": "http://localhost:9000",
"MINIO_ROOT_USER": "minio",
"MINIO_ROOT_PASSWORD": "minio123",
"OPENROUTER_API_KEY": "your-api-key"
}
}
}
}
Method 3: pip Install
Prerequisites: Same as Method 2, requires available PostgreSQL and MinIO/S3 services.
pip install paperlib-mcp
Configure MCP client (modify according to your actual service addresses):
{
"mcpServers": {
"paperlib": {
"command": "paperlib-mcp",
"args": [],
"env": {
"POSTGRES_HOST": "localhost",
"POSTGRES_USER": "paper",
"POSTGRES_PASSWORD": "paper",
"POSTGRES_DB": "paperlib",
"S3_ENDPOINT": "http://localhost:9000",
"MINIO_ROOT_USER": "minio",
"MINIO_ROOT_PASSWORD": "minio123",
"OPENROUTER_API_KEY": "your-api-key"
}
}
}
}
Method 4: Local Development
git clone https://github.com/your-org/paperlib-mcp.git
cd paperlib-mcp
uv sync
cp .env.example .env
# Edit .env
uv run python -m paperlib_mcp.server
π Available Tools
Basic Tools
| Tool | Description |
|---|---|
health_check |
System health check |
import_pdf |
Import PDF documents |
download_pdf |
Download PDF by title to local directory |
search_hybrid |
Hybrid search (recommended) |
get_document |
Get document metadata |
list_documents |
List all documents |
Graph Tools
| Tool | Description |
|---|---|
extract_graph_v1 |
Extract knowledge graph |
build_communities_v1 |
Build topic communities |
summarize_community_v1 |
Generate community summaries |
Writing Tools
| Tool | Description |
|---|---|
build_evidence_pack |
Build evidence pack |
draft_lit_review_v1 |
Generate review draft |
Full tool list (48+) available at docs/MCP_TOOLS_REFERENCE.md
π‘ Usage Examples
# Import PDF
> import_pdf file_path="/papers/study.pdf" title="Study Title"
# Search literature
> search_hybrid query="monetary policy" k=10
# Build knowledge graph
> extract_graph_v1 doc_id="abc123"
> build_communities_v1 level="macro"
# Generate review
> build_evidence_pack query="CBDC" k=40
> draft_lit_review_v1 pack_id=1
π Documentation
| Document | Description |
|---|---|
| DEPLOYMENT.md | Deployment Guide |
| ARCHITECTURE.md | System Architecture |
| EMBEDDING_SYSTEM.md | Embedding & Retrieval |
| KNOWLEDGE_GRAPH.md | Knowledge Graph |
| DATABASE_SCHEMA.md | Database Schema |
| MCP_TOOLS_REFERENCE.md | Tools API Reference |
π οΈ Tech Stack
| Component | Technology |
|---|---|
| MCP Protocol | FastMCP |
| Database | PostgreSQL 16 + pgvector |
| Object Storage | MinIO (S3 Compatible) |
| PDF Processing | PyMuPDF4LLM |
| Embedding Model | OpenRouter (text-embedding-3-small) |
| Graph Clustering | igraph + Leiden |
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
OPENROUTER_API_KEY |
β | - | OpenRouter API key |
POSTGRES_HOST |
β | localhost |
Database host |
POSTGRES_USER |
β | paper |
Database user |
POSTGRES_PASSWORD |
β | paper |
Database password |
POSTGRES_DB |
β | paperlib |
Database name |
S3_ENDPOINT |
β | http://localhost:9000 |
MinIO endpoint |
MINIO_ROOT_USER |
β | minio |
MinIO user |
MINIO_ROOT_PASSWORD |
β | minio123 |
MinIO password |
π License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.