ArXiv Search
Search arXiv papers with filters including categories, publication years, and pagination, returning paper details such as title, abstract, authors, and URL.
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., "@ArXiv Searchsearch for papers on large language models from 2024"
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.
ArXiv Search
Simple CLI tool and MCP server for searching arXiv papers via ArXiv Xplorer API.
Installation
# Using pip
pip install -e .
# Using uv
uv pip install -e .
# Or from GitHub
pip install git+https://github.com/hassenhamdi/arxiv-xplorer-mcp.gitRelated MCP server: research-mcp
CLI Usage
# Basic search
arxiv-search "large language models"
# With categories
arxiv-search "transformer" -c cs.CL cs.AI
# With years
arxiv-search "neural networks" -y 2023 2024
# Pagination
arxiv-search "attention" -p 2
# JSON output
arxiv-search "BERT" --jsonOptions
Option | Description |
| Search terms (required) |
| arXiv categories (e.g., cs.CL, cs.AI) |
| Publication years (e.g., 2023 2024) |
| Page number (default: 1) |
| Output raw JSON |
Popular Categories
Code | Description |
cs.CL | Computation and Language (NLP) |
cs.AI | Artificial Intelligence |
cs.CV | Computer Vision |
cs.LG | Machine Learning |
cs.RO | Robotics |
cs.CR | Cryptography and Security |
MCP Server
Configuration
Claude Desktop / Cline / OpenCode:
{
"mcpServers": {
"arxiv": {
"command": "python",
"args": ["-m", "arxiv_search.mcp_server"],
"cwd": "/path/to/arxiv_search"
}
}
}Tool: arxiv_search
Search arXiv papers with filters.
Parameters:
query(string, required): Search termscategories(list, optional): arXiv categoriesyears(list, optional): Publication yearspage(integer, optional): Page number (default: 1)
Returns: List of papers with fields: id, title, abstract, authors, date, categories, short_author, score, url
Development
# Install dev dependencies
pip install -e ".[dev]"
# Run CLI
python arxiv.py "query"
# Run MCP server
python -m arxiv_search.mcp_serverLicense
Personal Use Only - See LICENSE file
Disclaimer
Uses reverse-engineered API from arxivxplorer.com (unofficial)
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityFmaintenanceAn MCP server that provides access to arXiv papers through their API.Last updated4200MIT
- AlicenseAqualityBmaintenanceMCP server for searching, retrieving, and extracting full-text PDFs from arXiv papers.Last updated524MIT
- AlicenseAqualityBmaintenanceMCP server for searching and retrieving arXiv papers with full-text PDF extraction.Last updated51MIT
- Alicense-qualityBmaintenanceEnables searching arXiv and downloading papers via MCP tools, no API key required.Last updatedApache 2.0
Related MCP Connectors
IEEE Xplore MCP — BYOK wrapper over the IEEE Xplore Metadata Search API
ArXiv preprint search, daily category digest, and author-collaborator graph.
Search arXiv, fetch paper metadata, and read full-text content.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hassenhamdi/arxiv-xplorer-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server