semanticscholar

This MCP server exposes a set of tools that wrap the Semantic Scholar API to enable programmatic queries and retrievals via the MCP protocol. After starting the server, clients can invoke the following tools: search_semantic_scholar to search for papers using a query string, get_semantic_scholar_paper_details to retrieve detailed information about a specific paper, get_semantic_scholar_author_details to fetch details about an author, and get_semantic_scholar_citations_and_references to obtain a paper's citations and its references. The server acts as a bridge, translating MCP requests into Semantic Scholar API calls and returning structured results suitable for downstream agents or workflows.

Prerequisites:

• Python 3.10+ installed on your system
• Access to install Python packages (pip)

Installation steps:

1. Clone the repository (optional if you already have the code): git clone https://github.com/JackKuo666/semanticscholar-MCP-Server.git cd semanticscholar-mcp-server

2. Create and activate a virtual environment (recommended): python -m venv venv source venv/bin/activate # on macOS/Linux venv\Scripts\activate # on Windows

3. Install required Python packages: pip install semanticscholar mcp

4. Run the MCP server: python -m semanticscholar_mcp_server

Notes:

• The server may also be run directly via a script if you prefer: python semantics_cholar_server.py (depending on the deployment method used in your environment).
• Ensure network access to the Semantic Scholar API if running behind a proxy or firewall, and verify any API usage limits in your environment.

Tips and common considerations:

• The MCP server relies on the semanticscholar and mcp Python packages; ensure they are kept up to date to benefit from API updates and MCP enhancements.
• If you encounter authentication or rate-limit issues with the Semantic Scholar API, verify network access and consider adding caching at the client or server layer.
• When wiring this into a client (e.g., Claude Desktop, Cline, Windsurf), use the provided MCP server configuration format to ensure correct command and args are supplied.
• The configuration shown uses the module-based startup (python -m semanticscholar_mcp_server). If your deployment prefers a direct script start, adapt the command/arguments accordingly.
• You can adjust environment variables in the mcp_config under env to pass API keys or configuration options as needed by your deployment environment.