mcp-simple-arxiv
This MCP server lets clients search arXiv and retrieve paper/category information.
Search papers by title and abstract content with advanced arXiv syntax, including fielded title/abstract/author/category queries and boolean operators, with configurable max results.
Retrieve detailed data for a specific arXiv paper, including abstract and available formats/links.
List arXiv subject categories, optionally filtered by primary category, for use in searches.
Update the stored category taxonomy by fetching the latest version 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 "Deploy 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-arxiv search 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
Filter search results by submission date range
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: Research Paper Agent
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:
npx -y @smithery/cli install mcp-simple-arxiv --client claudeManual Installation
pip install mcp-simple-arxivUsage with Claude Desktop
Add this configuration to your claude_desktop_config.json:
(Mac OS)
{
"mcpServers": {
"simple-arxiv": {
"command": "python",
"args": ["-m", "mcp_simple_arxiv"]
}
}
}(Windows version):
{
"mcpServers": {
"simple-arxiv": {
"command": "C:\\Users\\YOUR_USERNAME\\AppData\\Local\\Programs\\Python\\Python311\\python.exe",
"args": [
"-m",
"mcp_simple_arxiv"
]
}
}
}After restarting Claude Desktop, the following capabilities will be available:
Searching Papers
You can ask Claude to search for papers using queries like:
Can you search arXiv for recent papers about large language models?The LLM can sort results by submission date, update date, or relevance:
Search arXiv for papers about transformers, sorted by relevance.Date filtering lets you focus on specific time periods:
Find papers about quantum computing published in 2024.
Search for recent machine learning papers from the last 6 months.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:
Can you show me the details for paper 2103.08220?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 WEB_DEPLOYMENT.md.
Development
To install for development:
git clone https://github.com/andybrandt/mcp-simple-arxiv
cd mcp-simple-arxiv
pip install -e .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
Available Tools
4 toolsget_paper_dataGet arXiv Paper DataBRead-only
Get detailed information about a specific paper including abstract and available formats.
Inputs: paper_id (required). Returns: result
list_categoriesList arXiv CategoriesARead-only
List all available arXiv categories and how to use them in search.
Inputs: primary_category. Returns: result
search_papersSearch arXiv PapersARead-only
Search for papers on arXiv by title and abstract content.
You can use advanced search syntax:
Search in title: ti:"search terms"
Search in abstract: abs:"search terms"
Search by author: au:"author name"
Combine terms with: AND, OR, ANDNOT
Filter by category: cat:cs.AI (use list_categories tool to see available categories)
Examples:
"machine learning" (searches all fields)
ti:"neural networks" AND cat:cs.AI (title with category)
au:bengio AND ti:"deep learning" (author and title)
Inputs: query (required), max_results. Returns: result
update_categoriesUpdate arXiv CategoriesA
Update the stored category taxonomy by fetching the latest version from arxiv.org
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: get_paper_data retrieves specific paper details, list_categories shows available categories, search_papers performs searches, and update_categories refreshes category data. There is no overlap in functionality that would cause confusion.
All tools follow a consistent verb_noun naming pattern (get_paper_data, list_categories, search_papers, update_categories). The naming is uniform and predictable throughout the set.
With 4 tools, this server is well-scoped for arXiv paper access. Each tool serves a clear purpose (retrieval, listing, searching, updating) without being too sparse or bloated, making it efficient for the domain.
The tools cover core arXiv operations: searching, retrieving paper details, and managing categories. A minor gap is the lack of tools for downloading papers or handling user-specific features like saved papers, but the basic workflow is well-supported.
Maintenance
Related MCP Connectors
Academic research MCP server for paper search, citation checks, graphs, and deep research.
An MCP server that provides congressional transcripts
An MCP server that gives your AI access to the source code and docs of all public github repos
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThis MCP server enables users to search for scientific papers on arXiv and retrieve detailed metadata for specific papers. It provides tools to perform search queries and fetch in-depth information using paper IDs.3Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA remote MCP server for searching arXiv papers, extracting paper details, and generating structured prompts for LLM agents.1-
- FlicenseAqualityDmaintenanceA streamlined MCP server that connects AI assistants to arXiv's vast collection of academic papers, enabling search, retrieval, and analysis of research papers.71-
- AlicenseAqualityCmaintenanceMCP server for searching and retrieving arXiv papers with full-text PDF extraction.52MIT