Scholarly

What is mcp-scholarly?

mcp-scholarly is a server built on the Model Context Protocol (MCP) that enables users to search for scholarly and academic articles. It currently integrates with arXiv and aims to expand its search capabilities to include other academic databases in the future.

How to use mcp-scholarly?

mcp-scholarly can be installed and configured for use with Claude Desktop or via Docker. It can also be installed automatically using Smithery.

Installation:

• Claude Desktop: Configure mcpServers in claude_desktop_config.json with the appropriate command and arguments for development, published servers, or Docker.
• Smithery: Use the command npx -y @smithery/cli install mcp-scholarly --client claude to install automatically.

Usage:

The server implements a search-arxiv tool that takes a "keyword" as a required string argument to search for articles.

Key Features of mcp-scholarly

• Academic Article Search: Specifically designed for searching scholarly and academic articles.
• arXiv Integration: Currently supports searching articles on arXiv.
• Extensible: Plans to add more scholarly vendors for broader search capabilities.
• MCP Server: Operates as a Model Context Protocol server, allowing integration with compatible clients like Claude Desktop.
• Easy Installation: Provides multiple installation methods including direct configuration, Smithery, and Docker.

Use Cases of mcp-scholarly

• Researchers: Quickly find relevant academic papers for their studies.
• Students: Access scholarly articles for assignments, theses, or general learning.
• Developers: Integrate academic search capabilities into their applications via the MCP server.
• Anyone needing academic information: A convenient way to search for accurate and peer-reviewed content.

FAQ from mcp-scholarly

Q: What is MCP? A: MCP stands for Model Context Protocol, which is a protocol that allows models to interact with external tools and services.

Q: Which academic databases are currently supported? A: Currently, mcp-scholarly supports searching articles on arXiv. More vendors are planned for future integration.

Q: How can I debug the mcp-scholarly server? A: You can use the MCP Inspector for debugging. Launch it via npm with a specific command that points to your mcp-scholarly directory, and then access the provided URL in your browser.

mcp-scholarly MCP server

A MCP server to search for 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 required string arguments

Quickstart

Install

Claude Desktop

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

or if you are using Docker

Installing via Smithery

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

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

Development

Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:

uv sync

2. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or 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 debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

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

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.