https://github.com/blazickjp/arxiv-mcp-server
A Model Context Protocol server for searching and analyzing arXiv papers
https://github.com/blazickjp/arxiv-mcp-server
Last synced: 4 months ago
JSON representation
A Model Context Protocol server for searching and analyzing arXiv papers
- Host: GitHub
- URL: https://github.com/blazickjp/arxiv-mcp-server
- Owner: blazickjp
- Created: 2024-11-29T16:34:00.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2024-11-29T17:19:12.000Z (12 months ago)
- Last Synced: 2024-11-29T17:32:58.489Z (12 months ago)
- Language: Python
- Size: 0 Bytes
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-mcp-servers - blazickjp/arxiv-mcp-server - Search ArXiv research papers via this MCP server, providing academic search functionality in the MCP ecosystem. ([Read more](/details/blazickjparxiv-mcp-server.md)) `mcp` `arxiv` `research` `search` (API Integration MCP Servers)
- awesome-mcp-zh - blazickjp/arxiv-mcp-server
- best-of-mcp-servers - GitHub - 79% open ยท โฑ๏ธ 19.08.2025) (Search & Data Extraction)
- awesome-mcp-servers - blazickjp/arxiv-mcp-server - Search ArXiv research papers (Legend / ๐ <a name="search"></a>Search)
- awesome-mcp-servers - blazickjp/arxiv-mcp-server - ArXiv็ ็ฉถ่ซๆใๆค็ดข (ใตใผใใผๅฎ่ฃ / ๐ <a name="search"></a>ๆค็ดขใปใใผใฟๆฝๅบ)
- awesome-arxiv - ArXiv MCP Server
- awesome-mcp-servers - ArXiv MCP Assistant - A Model Context Protocol server for searching and analyzing arXiv papers (Table of Contents / Research and Data)
- awesome-hacking-lists - blazickjp/arxiv-mcp-server - A Model Context Protocol server for searching and analyzing arXiv papers (Python)
- awesome-claude-mcp-servers - blazickjp/arxiv-mcp-server - Research paper search through ArXiv (Core Servers / Search Engines ๐)
- awesome-mcp - ArXiv MCP Server - The ArXiv MCP Server provides a bridge between AI assistants and arXiv's research repository through the Message Control Protocol (MCP) (MCP Servers / ๐ Search)
- toolsdk-mcp-registry - โ arxiv-mcp-server
- awesome-mcp-servers - ArXiv - Search ArXiv research papers (๐งฌ <a name="research-data"></a>Research & Data)
- metorial-index - ArXiv Server - Provides access to arXiv research papers via a straightforward MCP interface, enabling AI models to search and retrieve academic articles. (Scientific Research Tools)
- awesome-mcp-list - blazickjp/arxiv-mcp-server - mcp-server?style=social)](https://github.com/blazickjp/arxiv-mcp-server): Searches research papers on ArXiv. (Uncategorized / Uncategorized)
- awesome - blazickjp/arxiv-mcp-server - A Model Context Protocol server for searching and analyzing arXiv papers (Python)
- awesome-mcp-servers - **arxiv-mcp-server** - A Model Context Protocol server for searching and analyzing arXiv papers `http` `git` `github` `python` `ai` `pip install git+https://github.com/blazickjp/arxiv-mcp-server` (๐ Web Development)
README
[](https://twitter.com/JoeBlazick)
[](https://smithery.ai/server/arxiv-mcp-server)
[](https://www.python.org/downloads/)
[](https://github.com/blazickjp/arxiv-mcp-server/actions/workflows/tests.yml)
[](https://opensource.org/licenses/MIT)
[](https://pypi.org/project/arxiv-mcp-server/)
[](https://pypi.org/project/arxiv-mcp-server/)
# ArXiv MCP Server
> ๐ Enable AI assistants to search and access arXiv papers through a simple MCP interface.
The ArXiv MCP Server provides a bridge between AI assistants and arXiv's research repository through the Model Context Protocol (MCP). It allows AI models to search for papers and access their content in a programmatic way.
๐ค **[Contribute](https://github.com/blazickjp/arxiv-mcp-server/blob/main/CONTRIBUTING.md)** โข
๐ **[Report Bug](https://github.com/blazickjp/arxiv-mcp-server/issues)**
## โจ Core Features
- ๐ **Paper Search**: Query arXiv papers with filters for date ranges and categories
- ๐ **Paper Access**: Download and read paper content
- ๐ **Paper Listing**: View all downloaded papers
- ๐๏ธ **Local Storage**: Papers are saved locally for faster access
- ๐ **Prompts**: A Set of Research Prompts
## ๐ Quick Start
### Installing via Smithery
To install ArXiv Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/arxiv-mcp-server):
```bash
npx -y @smithery/cli install arxiv-mcp-server --client claude
```
### Installing Manually
Install using uv:
```bash
uv tool install arxiv-mcp-server
```
For development:
```bash
# Clone and set up development environment
git clone https://github.com/blazickjp/arxiv-mcp-server.git
cd arxiv-mcp-server
# Create and activate virtual environment
uv venv
source .venv/bin/activate
# Install with test dependencies
uv pip install -e ".[test]"
```
### ๐ MCP Integration
Add this configuration to your MCP client config file:
```json
{
"mcpServers": {
"arxiv-mcp-server": {
"command": "uv",
"args": [
"tool",
"run",
"arxiv-mcp-server",
"--storage-path", "/path/to/paper/storage"
]
}
}
}
```
For Development:
```json
{
"mcpServers": {
"arxiv-mcp-server": {
"command": "uv",
"args": [
"--directory",
"path/to/cloned/arxiv-mcp-server",
"run",
"arxiv-mcp-server",
"--storage-path", "/path/to/paper/storage"
]
}
}
}
```
## ๐ก Available Tools
The server provides four main tools:
### 1. Paper Search
Search for papers with optional filters:
```python
result = await call_tool("search_papers", {
"query": "transformer architecture",
"max_results": 10,
"date_from": "2023-01-01",
"categories": ["cs.AI", "cs.LG"]
})
```
### 2. Paper Download
Download a paper by its arXiv ID:
```python
result = await call_tool("download_paper", {
"paper_id": "2401.12345"
})
```
### 3. List Papers
View all downloaded papers:
```python
result = await call_tool("list_papers", {})
```
### 4. Read Paper
Access the content of a downloaded paper:
```python
result = await call_tool("read_paper", {
"paper_id": "2401.12345"
})
```
## ๐ Research Prompts
The server offers specialized prompts to help analyze academic papers:
### Paper Analysis Prompt
A comprehensive workflow for analyzing academic papers that only requires a paper ID:
```python
result = await call_prompt("deep-paper-analysis", {
"paper_id": "2401.12345"
})
```
This prompt includes:
- Detailed instructions for using available tools (list_papers, download_paper, read_paper, search_papers)
- A systematic workflow for paper analysis
- Comprehensive analysis structure covering:
- Executive summary
- Research context
- Methodology analysis
- Results evaluation
- Practical and theoretical implications
- Future research directions
- Broader impacts
## โ๏ธ Configuration
Configure through environment variables:
| Variable | Purpose | Default |
|----------|---------|---------|
| `ARXIV_STORAGE_PATH` | Paper storage location | ~/.arxiv-mcp-server/papers |
## ๐งช Testing
Run the test suite:
```bash
python -m pytest
```
## ๐ License
Released under the MIT License. See the LICENSE file for details.
---
Made with โค๏ธ by the Pearl Labs Team
