Semantic Scholar MCP server

This server implements the Model Context Protocol (MCP) to provide seamless access to the Semantic Scholar academic database. It enables searching for research papers, retrieving detailed information about specific publications and authors, and exploring citations and references - all directly through compatible MCP clients.

Installation Options

Quick Installation via Smithery

Install the server automatically using Smithery based on your preferred MCP client:

For Claude Desktop

npx -y @smithery/cli@latest install @JackKuo666/semanticscholar-mcp-server --client claude --config "{}"

For Cursor

On Mac/Linux, paste this into Settings → Cursor Settings → MCP → Add new server:

npx -y @smithery/cli@latest run @JackKuo666/semanticscholar-mcp-server --client cursor --config "{}" 

For Windsurf

npx -y @smithery/cli@latest install @JackKuo666/semanticscholar-mcp-server --client windsurf --config "{}"

For CLine

npx -y @smithery/cli@latest install @JackKuo666/semanticscholar-mcp-server --client cline --config "{}"

Manual Installation

1. Clone the repository:

   git clone https://github.com/JackKuo666/semanticscholar-MCP-Server.git
   cd semanticscholar-mcp-server
   

2. Install dependencies:

   pip install semanticscholar mcp
   

Usage

Starting the Server

Launch the server by running:

python semantic_scholar_server.py

The server will start and listen for MCP requests from compatible clients.

Available Tools

The MCP server provides the following capabilities:

• search_semantic_scholar: Search for papers using keywords
• get_semantic_scholar_paper_details: Retrieve detailed information about a specific paper
• get_semantic_scholar_author_details: Get information about a specific author
• get_semantic_scholar_citations_and_references: Retrieve citations and references for a paper

Client Configuration

Claude Desktop Configuration

Add this to your claude_desktop_config.json (Mac OS):

{
  "mcpServers": {
    "semanticscholar": {
      "command": "python",
      "args": ["-m", "semanticscholar_mcp_server"]
      }
  }
}

For Windows:

{
  "mcpServers": {
    "semanticscholar": {
      "command": "C:\\Users\\YOUR\\PATH\\miniconda3\\envs\\mcp_server\\python.exe",
      "args": [
        "D:\\code\\YOUR\\PATH\\semanticscholar-MCP-Server\\semanticscholar_server.py"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

CLine Configuration

{
  "mcpServers": {
    "semanticscholar": {
      "command": "bash",
      "args": [
        "-c",
        "source /home/YOUR/PATH/.venv/bin/activate && python /home/YOUR/PATH/semanticscholar_mcp_server.py"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

After configuration, your MCP client will be able to access Semantic Scholar data through this server.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.