📌Overview

Purpose: To provide a platform for searching and retrieving accurate academic articles from various scholarly sources.

Overview: The MCP Scholarly server is designed to facilitate efficient access to academic literature by enabling users to search for articles based on specific keywords. It focuses on enhancing the research capabilities of users by integrating with scholarly databases, with plans for future expansion to include more scholarly vendors.

Key Features:

Keyword Search Tool: Allows users to search for articles related to specified keywords, enhancing the ease of finding relevant academic publications.
Support for Multiple Configurations: Offers flexible installation options, including direct configuration, Docker integration, and automated installation via Smithery, catering to different user preferences and environments.

MCP Scholarly Server

A MCP server designed for searching accurate academic articles. More scholarly vendors will be added soon.

Components

Tools

The server implements one tool:

search-arxiv: Search arXiv for articles related to the given keyword.
- Takes "keyword" as a required string argument.

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration:

"mcpServers": {
  "mcp-scholarly": {
    "command": "uv",
    "args": [
      "--directory",
      "/Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly",
      "run",
      "mcp-scholarly"
    ]
  }
}

Published Servers Configuration:

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

Published Docker Servers Configuration:

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

Installing via Smithery

To automatically install mcp-scholarly for Claude Desktop via Smithery:

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

Development

Building and Publishing

To prepare the package for distribution:

Sync dependencies and update the lockfile:
```
uv sync
```
Build package distributions:
```
uv build
```
Publish to PyPI:
```
uv publish
```

Note: Set PyPI credentials via environment variables or command flags:

Token: --token or UV_PUBLISH_TOKEN
Username/Password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best experience, we recommend using the MCP Inspector.

Launch the MCP Inspector with the following command:

npx @modelcontextprotocol/inspector uv --directory /Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly run mcp-scholarly

Upon launching, the Inspector will display a URL to access in your browser for debugging.