scholarly
Overview
What is scholarly
The mcp-scholarly is a server designed for searching accurate academic articles, focusing primarily on providing access to scholarly content via a specific tool that queries arXiv for articles based on given keywords.
Use cases
This server can be utilized by researchers, students, or professionals seeking to find relevant academic literature quickly and efficiently. It enhances academic research workflows by enabling users to search and retrieve scholarly articles based on specific topics of interest.
How to use
Users can install the mcp-scholarly server either through configuration in Claude Desktop or via Docker. Additionally, it can be installed automatically using the Smithery CLI tool, which simplifies the setup process. After installation, users can search for articles by providing a keyword through the search-arxiv tool.
Key features
The key feature of the mcp-scholarly server is its ability to search the arXiv database for academic articles related to user-defined keywords. This focused search capability facilitates easy access to relevant scholarly literature.
Where to use
The mcp-scholarly server is suitable for use in academic settings, including universities and research institutions, as well as by individual researchers and students who require a tool for efficiently locating scholarly articles.
Content
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
Development/Unpublished Servers Configuration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" ] } } ```or if you are using Docker
Published Docker Servers Configuration
``` "mcpServers": { "mcp-scholarly": { "command": "docker", "args": [ "run", "--rm", "-i", "mcp/scholarly" ] } } ```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:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You’ll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--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.