Academic Paper Search

🚀 Academic Paper Search MCP Server

A server based on the Model Context Protocol (MCP) that supports searching and retrieving academic paper information from multiple sources.

This server offers the following capabilities to large language models (LLMs):

• Real-time academic paper search functionality
• Access to paper metadata and abstracts
• The ability to obtain available full-text content
• Structured data responses compliant with the MCP specification

Although primarily designed for integration with Anthropic's Claude desktop client, the MCP specification allows compatibility with other AI models and clients that support tool/function calling capabilities (e.g., OpenAI's API).

⚠️ Important Note

This software is in active development. Features and characteristics may change.

✨ Features

The server exposes the following tools:

• search_papers: Search for academic papers across multiple sources

  • Parameters:
    • query (str): Search query text
    • limit (int, optional): Maximum number of results (Default: 10)
  • Returns: A formatted string containing detailed paper information

• fetch_paper_details: Retrieve detailed information about a specific paper

  • Parameters:
    • paper_id (str): Paper identifier (DOI or Semantic Scholar ID)
    • source (str, optional): Data source ("crossref" or "semantic_scholar", Default: "crossref")
  • Returns: A formatted string containing comprehensive paper metadata, including:
    • Title, authors, year
    • DOI, title, abstract

• search_by_topic: Search for papers by topic

  • Parameters:
    • topic (str): Topic or keyword for the search
    • year_range (tuple, optional): Year range (e.g., (2015, 2023))
    • language (str, optional): Paper language (e.g., "English", "Chinese", etc.)
  • Returns: A list containing the titles and abstracts of matching papers

📦 Installation

Using Smithery

Install and run the server using the following commands:

smithery install @afrise/academic-search-mcp-server
smithery run

Manual Installation (Using uv)

1. Clone the repository: git clone https://github.com/yourusername/academic-paper-search.git
2. Install dependencies:

   cd academic-paper-search
   pip install -r requirements.txt
   

3. Set environment variables:

   export API_KEY=your_api_key_here  # If authentication is required
   

4. Start the server:

   python server.py
   

💻 Usage Examples

Basic Usage

Configure the server in the Claude desktop client:

1. Open the settings and navigate to the plugins section.
2. Add the following JSON configuration:

   {
     "server_url": "http://localhost:8000",
     "api_key": "your_api_key_here"
   }
   

🔧 Technical Details

The project uses the following technologies:

• Python MCP SDK: Provides MCP protocol support
• FastMCP: A high-performance MCP server framework
• httpx: Asynchronous HTTP client and server

API sources:

• Semantic Scholar API: Provides high-quality academic paper data
• Crossref API: Obtain publication metadata

📄 License

This project is licensed under the AGPL-3.0 license. Please refer to the LICENSE file for details.

🤝 Contribution Guidelines

Contributions are welcome! Here's how you can get involved:

1. Fork the repository: git clone https://github.com/yourusername/academic-paper-search.git
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Commit your changes: git commit -m 'Add amazing feature'
4. Push to the branch: git push origin feature/amazing-feature
5. Submit a Pull Request

Points to note:

• Follow the existing code style and conventions
• Add tests for new features
• Update relevant documentation
• Ensure that your changes comply with the AGPL-3.0 license terms

By participating in this project, you agree that your contributions will be released under the AGPL-3.0 license.