Scholarly MCP Server

Scholarly is a specialized search tool that helps you find accurate academic articles from reputable sources. It currently integrates with arXiv and Google Scholar to provide comprehensive access to scientific literature. With Scholarly, you can quickly search for academic papers, articles, and research publications using keywords. The tool returns relevant results with important metadata, making it easier to find credible sources for research, academic writing, or staying updated on scientific developments.

Overview

Scholarly is a Model Context Protocol (MCP) server that enables AI assistants to search for academic articles from reputable sources. It provides a streamlined way to access scholarly literature directly within your AI workflows.

Installation

You can install Scholarly in several ways depending on your setup:

Using Claude Desktop

For MacOS:

Edit the configuration file at: ~/Library/Application\ Support/Claude/claude_desktop_config.json

For Windows:

Edit the configuration file at: %APPDATA%/Claude/claude_desktop_config.json

Add the following to your configuration:

"mcpServers": {
  "mcp-scholarly": {
    "command": "uvx",
    "args": [
      "mcp-scholarly"
    ]
  }
}

Using Docker

If you prefer using Docker, add this configuration:

"mcpServers": {
  "mcp-scholarly": {
    "command": "docker",
    "args": [
      "run", "--rm", "-i",
      "mcp/scholarly"
    ]
  }
}

Using Smithery

For an automated installation with Claude Desktop, you can use Smithery:

npx -y @smithery/cli install mcp-scholarly --client claude

Development Setup

If you're developing or modifying the server:

Clone the repository
Use the development configuration:

"mcpServers": {
  "mcp-scholarly": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/your/mcp-scholarly/directory",
      "run",
      "mcp-scholarly"
    ]
  }
}

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, use the MCP Inspector:

npx @modelcontextprotocol/inspector uv --directory /path/to/your/mcp-scholarly/directory run mcp-scholarly

The Inspector will display a URL that you can access in your browser to begin debugging.

Usage

Once installed, you can use Scholarly by asking your AI assistant to search for academic articles. For example:

"Find academic papers about quantum computing"
"Search for recent research on climate change"
"Look up scholarly articles about machine learning"

The server will search for relevant academic articles and return the results with metadata such as title, authors, publication date, and abstract when available.