PaperMCP 智能学术论文检索系统

欢迎使用PaperMCP 智能学术论文检索系统！这是一个基于 Model Context Protocol (MCP) 的高级学术论文搜索服务器，专为研究员和教授设计。通过OpenAlex API和智能算法，为AI助手提供精准的学术文献检索能力，大幅提升科研效率。

Search academic papers with flexible filtering options:

- Keyword Search- Find papers by title, abstract, or full-text content
- Country Filter- Limit results to papers from specific countries (CN, US, GB, etc.)
- Year Filter- Search papers from specific publication years
- Result Limit- Control the number of results (up to 50 papers)
- Sort Options- Sort by citation count, publication date, or relevance
- Open Access Filter- Find only freely accessible papers

Get comprehensive details for each paper:

- Basic Info- Title, authors, publication year, document type
- Abstract- Full abstract text with intelligent reconstruction from inverted index
- Publication Details- Journal/venue, DOI, URLs
- Citation Data- Citation count and related works
- Institutional Info- Author affiliations and institutions
- Subject Classification- Topics, subfields, fields, and domains
- Open Access Status- OA status and APC (Article Processing Charge) information

- Institution-based Filtering- Find papers from specific countries' institutions
- Temporal Filtering- Search within specific publication years
- Access-based Filtering- Filter by open access availability
- Quality Indicators- Sort by citation impact or publication date

Seamless integration with MCP-compatible clients (like Claude) for intelligent academic research

Before getting started, please ensure you have:

- Requires Node.js version >= 18
- Download and install fromnodejs.org

If you're using Claude Desktop, you can quickly install viaSmithery:

npx -y @smithery/cli install @guangxiangdebizi/paper-mcp --client claude

git clone https://github.com/guangxiangdebizi/PaperMCP.git cd PaperMCP

OPENALEX_EMAIL=your_email@example.com

npx supergateway --stdio "node build/index.js" --port 3100

{ "mcpServers": { "paper-search-server": { "url": "http://localhost:3100/sse", // If using Supergateway "type": "sse", "disabled": false, "autoApprove": [ "paper_search" ] } } }

If using stdio mode directly (without Supergateway), configure as follows:

{ "mcpServers": { "paper-search-server": { "command": "C:/path/to/PaperMCP/build/index.js", // Modify to actual path "type": "stdio", "disabled": false, "autoApprove": [ "paper_search" ] } } }

Here are some example queries using the PaperMCP server:

"Search for papers about machine learning published in 2024"

"Find papers about artificial intelligence from Chinese institutions in 2023"

"Search for papers about LLM from US universities in the last 2 years"

"Find the most-cited papers about deep learning from 2022, limited to 20 results"

"Search for open access papers about natural language processing from 2024"

"Find papers about computer vision published in 2023, sorted by citation count"

"Help me find recent papers about transformer architectures for my literature review"

"Search for papers about quantum computing from different countries to analyze research trends"

"Find papers that combine AI and biology, focusing on recent publications"

"Compare recent AI research output between China and the US by finding papers from both countries in 2024"

"Show me how research in reinforcement learning has evolved by finding papers from 2020-2024"

"Find highly-cited open access papers in machine learning to understand accessible research trends"

This will use thepaper_searchtool to retrieve comprehensive academic paper information.

The PaperMCP server supports the following search parameters:

This server uses theOpenAlex API, which provides:

- 260M+ papersfrom across all disciplines
- Real-time updateswith new publications
- Comprehensive metadataincluding citations, authors, institutions
- Open access informationand APC data
- Subject classificationat multiple levels
- Institution and country datafor geographic analysis
- Author Search- Find papers by specific authors
- Institution Search- Search within specific institutions
- Journal/Venue Filtering- Filter by publication venue
- Citation Network Analysis- Explore citation relationships
- Concept-based Search- Search by research concepts and topics
- Export Functionality- Export results in various formats (BibTeX, etc.)

This project is licensed under the MIT License. See theLICENSEfile for details.

- Name: Xingyu_Chen
- Email:guangxiangdebizi@gmail.com
- GitHub:guangxiangdebizi

This project uses theOpenAlexAPI, a free and open catalog of scholarly papers, authors, institutions, and more. Special thanks to the OpenAlex team for providing this invaluable resource to the research community.

Anonymous, read-only, source-backed Buddhist scripture search, passage guidance, explanation, and one-time practice planning through four production MCP tools.