what is mcp-scholarly?
mcp-scholarly is a server designed to search for accurate academic articles, providing users with a reliable tool for academic research.
how to use mcp-scholarly?
To use mcp-scholarly, you can install it via Claude Desktop or Docker, and then utilize the search-arxiv tool by providing a keyword to find relevant articles.
key features of mcp-scholarly?
- Searches for academic articles on arXiv based on keywords.
- Supports installation via multiple platforms including Docker and Claude Desktop.
- Easy configuration for both development and published servers.
use cases of mcp-scholarly?
- Researchers looking for specific academic papers.
- Students needing reliable sources for their assignments.
- Academics wanting to stay updated with the latest research in their field.
FAQ from mcp-scholarly?
- What types of articles can I find?
You can find a wide range of academic articles across various disciplines available on arXiv.
- Is mcp-scholarly free to use?
Yes! mcp-scholarly is free to use for everyone.
- How do I install mcp-scholarly?
You can install it via Claude Desktop or Docker by following the provided installation instructions.
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Development/Unpublished Servers Configuration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.