The mcp-simple-arxiv server provides access to arXiv papers through its API, enabling:
Search for papers: Search by title, abstract, author, or category using advanced syntax (e.g.,
ti:"neural networks" AND cat:cs.AI)Get paper details: Retrieve information about specific papers, including title, authors, abstract, and links to PDF/HTML formats
List categories: View available arXiv categories for use in search queries
Update categories: Fetch the latest arXiv category taxonomy from arxiv.org
Provides access to scientific papers on arXiv through their API, allowing users to search for papers by title and abstract content, retrieve paper metadata and abstracts, access links to available paper formats (PDF/HTML), and explore arXiv categories.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-simple-arxivsearch for recent papers on quantum computing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-simple-arxiv
An MCP server that provides access to arXiv papers through their API.
Features
This server allows LLM clients (like Claude Desktop) to:
Search for scientific papers on arXiv by title and abstract content
Control search result sorting (by submission date, update date, or relevance)
See total matching results count to gauge search specificity
Get paper metadata and abstracts
Retrieve full paper text as Markdown (converted from PDF)
Access links to available paper formats (PDF/HTML)
Browse and search arXiv subject categories
To use the web version just add this connector to Claude.ai https://mcp.andybrandt.net/arxiv . You can also install & use it locally.
Related MCP server: bioRxiv-MCP-Server
Installation and Deployment
This server can be run in two modes: as a local stdio server for desktop clients or as a network-accessible web server.
Installing via Smithery
To install Simple Arxiv for Claude Desktop automatically via Smithery:
Manual Installation
Usage with Claude Desktop
Add this configuration to your claude_desktop_config.json:
(Mac OS)
(Windows version):
After restarting Claude Desktop, the following capabilities will be available:
Searching Papers
You can ask Claude to search for papers using queries like:
The LLM can sort results by submission date, update date, or relevance:
Search results include:
Total number of matching papers (e.g., "Found 15,234 total results, showing first 10")
Paper title, authors, and arXiv ID
Categories (primary and additional)
Publication date
Abstract preview
Getting Paper Details
Once you have a paper ID, you can ask for more details:
This will return:
Full paper title
Authors
Publication and update dates
Journal reference (if available)
Paper abstract
Links to available formats (PDF/HTML)
For web deployment see .
Development
To install for development:
arXiv API Guidelines
This server follows arXiv API usage guidelines:
Rate limiting to max 1 request per 3 seconds
Single connection at a time
Proper error handling and retry logic
License
MIT