Which integrations are available for this server?

Allows searching arXiv for academic papers with date filtering, relevance ranking, and full-text extraction. Provides Jupyter integration for interactive search, analysis, and visualization of arXiv papers. Offers LangChain tools for integrating arXiv paper search and cache management into LangChain agents. Includes a Streamlit dashboard for interactive browsing and analysis of arXiv search results.

How do I use arXiv Research MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@arXiv Research MCP Server find recent papers on quantum machine learning" 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 Research MCP Server

by borderlessboy

Overview Schema Related Servers Score Discussions

Python

Remote

arXiv Research MCP Server

A comprehensive Model Context Protocol (MCP) server for searching and analyzing academic papers from arXiv with AI-powered relevance ranking and full-text extraction.

Features

Smart Search: Search arXiv with date filtering and relevance ranking
Full Text Extraction: Download and extract complete paper content
Caching: Intelligent caching to reduce API calls
Multiple Integrations: Works with Claude, LangChain, Streamlit, and more
Batch Processing: Process multiple research topics efficiently
API Wrapper: REST API for easy integration
Jupyter Integration: Interactive analysis and visualization tools
Relevance Ranking: TF-IDF based ranking for better results
PDF Processing: Multi-method text extraction from PDFs

Quick Start

Installation

# Clone the repository
git clone https://github.com/borderlessboy/arxiv-research-mcp
cd arxiv-research-mcp

# Install dependencies
pip install -r requirements.txt

# Create environment configuration
# cp .env.example .env  # Create .env file with your configuration

Basic Usage

# Run the MCP server
python scripts/run_server.py

# Or use the Streamlit dashboard
streamlit run integrations/streamlit_app.py

Docker Usage

The project includes a Dockerfile for easy containerized deployment.

Quick Start with Docker

# Build the Docker image
docker build -t arxiv-research-mcp .

# Run the container
docker run -p 8090:8090 arxiv-research-mcp

Docker with Custom Configuration

# Build with custom tag
docker build -t arxiv-research-mcp:latest .

# Run with custom port mapping
docker run -p 8080:8090 arxiv-research-mcp

# Run with volume for persistent cache
docker run -p 8090:8090 -v $(pwd)/cache:/app/cache arxiv-research-mcp

# Run with environment variables
docker run -p 8090:8090 \
  -e CACHE_ENABLED=true \
  -e CACHE_TTL_HOURS=24 \
  -e LOG_LEVEL=INFO \
  arxiv-research-mcp

Docker Compose (Recommended)

The project includes a docker-compose.yml file for easy deployment:

# Start the service
docker-compose up -d

# View logs
docker-compose logs -f

# Stop the service
docker-compose down

Or create a custom docker-compose.yml:

services:
  arxiv-research-mcp:
    build: .
    ports:
      - "8090:8090"
    volumes:
      - ./cache:/app/cache
    environment:
      - CACHE_ENABLED=true
      - CACHE_TTL_HOURS=24
      - LOG_LEVEL=INFO
    restart: unless-stopped

# Start the service
docker-compose up -d

# View logs
docker-compose logs -f

# Stop the service
docker-compose down

Docker Development

# Build for development with all dependencies
docker build -t arxiv-research-mcp:dev .

# Run with mounted source code for development
docker run -p 8090:8090 \
  -v $(pwd)/src:/app/src \
  -v $(pwd)/config:/app/config \
  -v $(pwd)/cache:/app/cache \
  arxiv-research-mcp:dev

Installation Options

Docker Installation (Recommended)

# Quick start with Docker
docker build -t arxiv-research-mcp .
docker run -p 8090:8090 arxiv-research-mcp

Full Installation

pip install "arxiv-research-mcp[all]"

Specific Components

# API server only
pip install "arxiv-research-mcp[api]"

# Jupyter integration
pip install "arxiv-research-mcp[jupyter]"

# Dashboard
pip install "arxiv-research-mcp[dashboard]"

# LangChain integration
pip install "arxiv-research-mcp[langchain]"

Usage Examples

1. Basic MCP Server Usage

from src.server import search_arxiv_papers_tool

# Search for papers
result = await search_arxiv_papers_tool({
    "query": "transformer models",
    "max_results": 10,
    "years_back": 4,
    "include_full_text": True
})

2. LangChain Integration

from integrations.langchain_tool import ResearchAgent

agent = ResearchAgent()
result = agent.research_topic("quantum machine learning")

3. Jupyter Analysis

from integrations.jupyter_helper import search_papers

# Search and analyze
helper = await search_papers("machine learning", max_results=20)

# Create visualizations
fig = helper.create_publication_timeline()
plt.show()

4. Streamlit Dashboard

streamlit run integrations/streamlit_app.py

Configuration

Create a .env file with your settings:

# Server Configuration
SERVER_NAME=arxiv-research-server
LOG_LEVEL=INFO

# arXiv API Configuration
ARXIV_REQUEST_TIMEOUT=30
ARXIV_MAX_RETRIES=3

# Caching
CACHE_ENABLED=true
CACHE_TTL_HOURS=24

# Content Processing
MAX_FULL_TEXT_LENGTH=50000
DEFAULT_MAX_RESULTS=10
DEFAULT_YEARS_BACK=4

API Reference

MCP Tools

`search_arxiv_papers`

Search for academic papers with relevance ranking.

Parameters:

query (string): Search query
max_results (integer, default: 10): Maximum papers to return
years_back (integer, default: 4): Years to search back
include_full_text (boolean, default: true): Include full paper text

`clear_cache`

Clear all cached search results.

`get_cache_stats`

Get cache statistics and information.

LangChain Tools

`ArxivResearchTool`

Search arXiv papers with LangChain integration.

`ArxivCacheManagementTool`

Manage cache with LangChain integration.

Advanced Features

Relevance Ranking

The server uses TF-IDF vectorization and cosine similarity to rank papers by relevance to your query.

PDF Processing

Multiple extraction methods (PyPDF2, pdfplumber) ensure robust text extraction from PDFs.

Caching System

Intelligent caching reduces API calls and improves response times.

Batch Processing

Process multiple research topics efficiently with the batch processor.

Docker Deployment

The project includes a production-ready Dockerfile with:

Lightweight Python 3.11-slim base image
Optimized layer caching for faster builds
Pre-configured HTTP server on port 8090
Volume support for persistent caching
Environment variable configuration

Development

Running Tests

pytest tests/

Code Quality

black src/ tests/
flake8 src/ tests/
mypy src/

Building

python setup.py build

Docker Development

# Build development image
docker build -t arxiv-research-mcp:dev .

# Run with source code mounted for development
docker run -p 8090:8090 \
  -v $(pwd)/src:/app/src \
  -v $(pwd)/config:/app/config \
  -v $(pwd)/cache:/app/cache \
  arxiv-research-mcp:dev

# Run tests in Docker
docker run arxiv-research-mcp:dev pytest tests/

Architecture

arxiv-research-mcp/
├── src/
│   ├── server.py              # Main MCP server
│   ├── models/                # Data models
│   ├── services/              # Core services
│   └── utils/                 # Utility functions
├── integrations/              # External integrations
├── scripts/                   # Utility scripts
├── tests/                     # Test suite
└── examples/                  # Usage examples

Documentation

For detailed documentation and guides, see the Docs/ directory:

MCPO Integration Guide - Complete guide for MCPO integration
Port Running Guide - How to run the server on different ports
README for MCPO - MCPO-specific documentation
Bug Fixes Summary - Summary of bug fixes and improvements
Code Cleanup Summary - Documentation of code cleanup and optimization
Docker Setup Guide - Comprehensive Docker deployment guide
License Information - License details and compliance guide

Contributing

Fork the repository
Create a feature branch
Make your changes
Add tests for new functionality
Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Troubleshooting

Docker Issues

Port already in use:

# Use a different port
docker run -p 8080:8090 arxiv-research-mcp

Permission denied:

# Run with proper permissions
sudo docker run -p 8090:8090 arxiv-research-mcp

Build fails:

# Clean build
docker system prune -a
docker build --no-cache -t arxiv-research-mcp .

Container exits immediately:

# Check logs
docker logs <container_id>
# Run interactively
docker run -it arxiv-research-mcp /bin/bash

Support

Issues: GitHub Issues
Documentation: GitHub Wiki
Discussions: GitHub Discussions

Acknowledgments

arXiv for providing the academic paper database
MCP (Model Context Protocol) for the server framework
The open-source community for the various libraries used

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

0dRelease cycle

2Releases (12mo)

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

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/borderlessboy/arxiv-research-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server