📚 Academic MCP

English | 中文

🔬 academic-mcp is a Python-based MCP server that enables users to search, download, and read academic papers from various platforms. It provides three main tools:

• 🔎 paper_search: Search papers across multiple academic databases
• 📥 paper_download: Download paper PDFs, return paths of downloaded files
• 📖 paper_read: Extract and read text content from papers

📑 Table of Contents

• 🎬 Screenshot
• 📝 TODO
• ✨ Features
• 📦 Installation
  • ⚡ Quick Start
  • 🛠️ For Development
• 🚀 Usage
  • 🔎 Search Papers
  • 📥 Download Papers
  • 📖 Read Papers
  • ⚙️ Environment Variables
• 🤝 Contributing
• 📄 License

✨ Features

• 🌐 Multi-Source Support: Search and download papers from 19+ academic databases including arXiv, PubMed, PubMed Central, bioRxiv, medRxiv, Google Scholar, IACR ePrint Archive, Semantic Scholar, CrossRef, Science Direct, Springer, IEEE Xplore, Scopus, CORE, and more.
• 🎯 Unified Interface: All platforms accessible through consistent paper_search, paper_download, and paper_read tools.
• 📊 Standardized Output: Papers are returned in a consistent dictionary format via the Paper class.
• ⚡ Asynchronous Operations: Efficiently handles concurrent searches and downloads using httpx and async/await.
• 🔌 MCP Integration: Compatible with MCP clients for LLM context enhancement.
• 🧩 Extensible Design: Easily add new academic platforms by extending the sources module.

🎬 Screenshot

📝 Supported Academic Platforms

✅ Fully Implemented (19 sources)

Free & Open Access:

• arXiv - Pre-print repository for physics, mathematics, CS, and more
• PubMed - Biomedical literature database
• PubMed Central (PMC) - Free full-text biomedical and life sciences articles
• bioRxiv - Pre-print server for biology
• medRxiv - Pre-print server for health sciences
• Semantic Scholar - AI-powered research tool
• CrossRef - DOI registration agency and metadata provider
• Google Scholar - Academic search engine
• IACR ePrint Archive - Cryptology pre-prints
• CORE - Open access research papers aggregator

API Key Required:

• Science Direct - Elsevier's full-text scientific database (requires Elsevier API key)
• Springer Link - Springer's scientific publications (requires Springer API key)
• IEEE Xplore - IEEE's digital library (requires IEEE API key)
• Scopus - Elsevier's abstract and citation database (requires Scopus API key)

Institutional Access Required:

• ACM Digital Library - ACM's computing literature (no public API)
• Web of Science - Clarivate's citation database (requires subscription)
• JSTOR - Digital library of academic journals (no public API)
• ResearchGate - Academic social network (no official API)

Retired Services:

• Microsoft Academic - Service retired December 31, 2021 (placeholder implementation)

📦 Installation

academic-mcp can be installed using uv or pip. Below are detailed installation guides for different scenarios.

⚡ Quick Install

Install the package:

pip install academic-mcp

Start the MCP server:

academic-mcp

🔧 MCP Client Configuration

Choose your MCP client and follow the configuration steps:

{
  "mcpServers": {
    "academic-mcp": {
      "command": "python",
      "args": ["-m", "academic_mcp"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "",
        "SCIENCEDIRECT_API_KEY": "",
        "SPRINGER_API_KEY": "",
        "IEEE_API_KEY": "",
        "SCOPUS_API_KEY": "",
        "CORE_API_KEY": "",
        "WOS_API_KEY": "",
        "ACADEMIC_MCP_ENABLED_SOURCES": "arxiv,pubmed,pmc,biorxiv,medrxiv,semantic,core,crossref,google_scholar,iacr",
        "ACADEMIC_MCP_DISABLED_SOURCES": "ieee,scopus,springer,sciencedirect,wos,acm,jstor",
        "ACADEMIC_MCP_DOWNLOAD_PATH": "./downloads"
      }
    }
  }
}

{
  "mcpServers": {
    "academic-mcp": {
      "command": "academic-mcp",
      "args": [],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "",
        "SCIENCEDIRECT_API_KEY": "",
        "SPRINGER_API_KEY": "",
        "IEEE_API_KEY": "",
        "SCOPUS_API_KEY": "",
        "CORE_API_KEY": "",
        "WOS_API_KEY": "",
        "ACADEMIC_MCP_ENABLED_SOURCES": "arxiv,pubmed,pmc,biorxiv,medrxiv,semantic,core,crossref,google_scholar,iacr",
        "ACADEMIC_MCP_DISABLED_SOURCES": "ieee,scopus,springer,sciencedirect,wos,acm,jstor",
        "ACADEMIC_MCP_DOWNLOAD_PATH": "./downloads"
      }
    }
  }
}

# Check if academic-mcp is loaded
claude mcp list

# Test the server
claude mcp test academic-mcp

{
  "cline.mcpServers": {
    "academic-mcp": {
      "command": "academic-mcp",
      "args": [],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "",
        "SCIENCEDIRECT_API_KEY": "",
        "SPRINGER_API_KEY": "",
        "IEEE_API_KEY": "",
        "SCOPUS_API_KEY": "",
        "CORE_API_KEY": "",
        "WOS_API_KEY": "",
        "ACADEMIC_MCP_ENABLED_SOURCES": "arxiv,pubmed,pmc,biorxiv,medrxiv,semantic,core,crossref,google_scholar,iacr",
        "ACADEMIC_MCP_DISABLED_SOURCES": "ieee,scopus,springer,sciencedirect,wos,acm,jstor",
        "ACADEMIC_MCP_DOWNLOAD_PATH": "./downloads"
      }
    }
  }
}

{
  "cline.mcpServers": {
    "academic-mcp": {
      "command": "academic-mcp",
      "args": [],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "",
        "SCIENCEDIRECT_API_KEY": "",
        "SPRINGER_API_KEY": "",
        "IEEE_API_KEY": "",
        "SCOPUS_API_KEY": "",
        "CORE_API_KEY": "",
        "WOS_API_KEY": "",
        "ACADEMIC_MCP_ENABLED_SOURCES": "arxiv,pubmed,pmc,biorxiv,medrxiv,semantic,core,crossref,google_scholar,iacr",
        "ACADEMIC_MCP_DISABLED_SOURCES": "ieee,scopus,springer,sciencedirect,wos,acm,jstor",
        "ACADEMIC_MCP_DOWNLOAD_PATH": "./downloads"
      }
    }
  }
}

{
  "context_servers": {
    "academic-mcp": {
      "command": {
        "path": "academic-mcp",
        "args": []
      },
      "settings": {
        "env": {
          "SEMANTIC_SCHOLAR_API_KEY": "",
          "SCIENCEDIRECT_API_KEY": "",
          "SPRINGER_API_KEY": "",
          "IEEE_API_KEY": "",
          "SCOPUS_API_KEY": "",
          "CORE_API_KEY": "",
          "WOS_API_KEY": "",
          "ACADEMIC_MCP_ENABLED_SOURCES": "arxiv,pubmed,pmc,biorxiv,medrxiv,semantic,core,crossref,google_scholar,iacr",
          "ACADEMIC_MCP_DISABLED_SOURCES": "ieee,scopus,springer,sciencedirect,wos,acm,jstor",
          "ACADEMIC_MCP_DOWNLOAD_PATH": "./downloads"
        }
      }
    }
  }
}

academic-mcp
# or
python -m academic_mcp

⚙️ Environment Variables

API Keys (optional - only for premium services):

• SEMANTIC_SCHOLAR_API_KEY: Semantic Scholar (Get API Key)
• SCIENCEDIRECT_API_KEY: Elsevier Science Direct (Get API Key)
• SPRINGER_API_KEY: Springer Nature (Get API Key)
• IEEE_API_KEY: IEEE Xplore (Get API Key)
• SCOPUS_API_KEY: Elsevier Scopus (Get API Key)
• CORE_API_KEY: CORE aggregator (Get API Key)
• WOS_API_KEY: Web of Science (requires institutional subscription)

General Settings:

• ACADEMIC_MCP_DOWNLOAD_PATH: Directory for downloaded PDFs (default: ./downloads)

Source Control:

• ACADEMIC_MCP_ENABLED_SOURCES: Comma-separated list to enable specific sources (whitelist)
• ACADEMIC_MCP_DISABLED_SOURCES: Comma-separated list to disable specific sources (blacklist)
• If both are set, ACADEMIC_MCP_ENABLED_SOURCES takes precedence
• If neither is set, all 18 sources are enabled by default

Available Source Names (18 total):

🚀 Usage

Once configured, academic-mcp provides three main tools accessible through Claude Desktop or any MCP-compatible client.

1. Search Papers (paper_search)

Search for academic papers across multiple sources:

Basic Search Examples:

# Search arXiv for machine learning papers
paper_search([
    {"searcher": "arxiv", "query": "machine learning", "max_results": 5}
])

# Search PubMed Central for biomedical papers
paper_search([
    {"searcher": "pmc", "query": "cancer treatment", "max_results": 5}
])

# Search CORE for open access papers
paper_search([
    {"searcher": "core", "query": "climate change", "max_results": 5}
])

Multi-Platform Search:

# Search multiple platforms simultaneously
paper_search([
    {"searcher": "arxiv", "query": "deep learning", "max_results": 5},
    {"searcher": "pubmed", "query": "cancer immunotherapy", "max_results": 3},
    {"searcher": "pmc", "query": "diabetes treatment", "max_results": 3},
    {"searcher": "semantic", "query": "climate change", "max_results": 4, "year": "2020-2023"}
])

Premium Sources (require API keys):

# Search IEEE Xplore (requires IEEE_API_KEY)
paper_search([
    {"searcher": "ieee", "query": "neural networks", "max_results": 5}
])

# Search Springer Link (requires SPRINGER_API_KEY)
paper_search([
    {"searcher": "springer", "query": "quantum computing", "max_results": 5}
])

# Search Scopus (requires SCOPUS_API_KEY)
paper_search([
    {"searcher": "scopus", "query": "artificial intelligence", "max_results": 5}
])

Search All Platforms:

# Search all platforms (omit "searcher" parameter)
paper_search([
    {"query": "quantum computing", "max_results": 10}
])

2. Download Papers (paper_download)

Download paper PDFs using their identifiers:

# Download from free sources
paper_download([
    {"searcher": "arxiv", "paper_id": "2106.12345"},
    {"searcher": "pubmed", "paper_id": "32790614"},
    {"searcher": "pmc", "paper_id": "PMC7419405"},
    {"searcher": "biorxiv", "paper_id": "10.1101/2020.01.01.123456"},
    {"searcher": "semantic", "paper_id": "DOI:10.18653/v1/N18-3011"}
])

# Download from CORE (open access)
paper_download([
    {"searcher": "core", "paper_id": "123456789"}
])

Note: Premium sources (IEEE, Springer, Science Direct, Scopus) require institutional access or subscriptions for PDF downloads.

3. Read Papers (paper_read)

Extract and read text content from papers:

# Read papers from free sources
paper_read(searcher="arxiv", paper_id="2106.12345")
paper_read(searcher="pubmed", paper_id="32790614")
paper_read(searcher="pmc", paper_id="PMC7419405")
paper_read(searcher="biorxiv", paper_id="10.1101/2020.01.01.123456")
paper_read(searcher="semantic", paper_id="DOI:10.18653/v1/N18-3011")
paper_read(searcher="core", paper_id="123456789")

🛠️ For Development

For developers who want to modify the code or contribute:

1. Setup Environment:

   # Install uv if not installed
   curl -LsSf https://astral.sh/uv/install.sh | sh
   
   # Clone repository
   git clone https://github.com/LinXueyuanStdio/academic-mcp.git
   cd academic-mcp
   
   # Create and activate virtual environment
   uv venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
   

2. Install Dependencies:

   # Install dependencies (recommended)
   uv pip install -e .
   
   # Add development dependencies (optional)
   uv pip install pytest flake8
   

🤝 Contributing

We welcome contributions! Here's how to get started:

1. Fork the Repository: Click "Fork" on GitHub.

2. Clone and Set Up:

   git clone https://github.com/yourusername/academic-mcp.git
   cd academic-mcp
   uv pip install -e .  # Install in development mode
   

3. Make Changes:

   • Add new platforms in academic_mcp/sources/.
   • Update tests in tests/.

4. Submit a Pull Request: Push changes and create a PR on GitHub.

📄 License

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

Happy researching with academic-mcp! If you encounter issues, open a GitHub issue.