Skip to main content

MCP server for accesing arXiv API

Project description

arXiv MCP Server

MCP Compatible Python License smithery badge

A Model Context Protocol (MCP) server that enables interacting with the arXiv API using natural language.

Features

  • Retrieve metadata about scholarly articles hosted on arXiv.org
  • Download articles in PDF format to the local machine
  • Search arXiv database for a particular query
  • Retrieve articles and load them into a large language model (LLM) context

Tools

  • get_article_url
    • Retrieve the URL of an article hosted on arXiv.org based on its title
      • title (String): Article title
  • download_article
    • Download the article hosted on arXiv.org as a PDF file
      • title (String): Article title
  • load_article_to_context
    • Load the article hosted on arXiv.org into context of a LLM
      • title (String): Article title
  • get_details
    • Retrieve metadata of an article hosted on arXiv.org based on its title
      • title (String): Article title
  • search_arxiv
    • Performs a search query on the arXiv API based on specified parameters and returns matching article metadata
      • all_fields (String): General keyword search across all metadata fields
      • title (String): Keyword(s) to search for within the titles of articles
      • author (String): Author name(s) to filter results by
      • abstract (String): Keyword(s) to search for within article abstracts
      • start (int): Index of the first result to return

Setup

MacOS

Clone the repository

git clone https://github.com/prashalruchiranga/arxiv-mcp-server.git
cd arxiv-mcp-server

Install uv package manager. For more details on installing, visit the official uv documentation.

# Using Homebrew
brew install uv

# or
curl -LsSf https://astral.sh/uv/install.sh | sh

Create and activate virtual environment.

uv venv --python=python3.13
source .venv/bin/activate

Install development dependencies.

uv sync

Windows

Install uv package manager. For more details on installing, visit the official uv documentation.

# Use irm to download the script and execute it with iex
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Close and reopen the shell, then clone the repository.

git clone https://github.com/prashalruchiranga/arxiv-mcp-server.git
cd arxiv-mcp-server

Create and activate virtual environment.

uv venv --python=python3.13
source .venv\Scripts\activate

Install development dependencies.

uv sync

Usage with Claude Desktop

To enable this integration, add the server configuration to your claude_desktop_config.json file. Make sure to create the file if it doesn’t exist.

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Roaming/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "arxiv-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/PARENT/FOLDER/arxiv-mcp-server/src/arxiv_server",
        "run",
        "server.py"
      ],
      "env": {
        "DOWNLOAD_PATH": "/ABSOLUTE/PATH/TO/DOWNLOADS/FOLDER"
      }
    }
  }
}

You may need to put the full path to the uv executable in the command field. You can get this by running which uv on MacOS or where uv on Windows.

Example Prompts

Can you get the details of 'Reasoning to Learn from Latent Thoughts' paper?
Get the papers authored or co-authored by Yann Lecun on convolutional neural networks
Download the attention is all you need paper
Can you get the papers by Andrew NG which have 'convolutional neural networks' in title?
Can you display the paper?
List the titles of papers by Yann LeCun. Paginate through the API until there are 30 titles

License

Licensed under MIT. See the LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iflow_mcp_arxiv_mcp_server-0.1.0.tar.gz (6.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

iflow_mcp_arxiv_mcp_server-0.1.0-py3-none-any.whl (7.6 kB view details)

Uploaded Python 3

File details

Details for the file iflow_mcp_arxiv_mcp_server-0.1.0.tar.gz.

File metadata

File hashes

Hashes for iflow_mcp_arxiv_mcp_server-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9fe848767e9356c8a638d8b95caf2acdd242cc2e4638f5b6b1ca3ef8c04c9ccc
MD5 ceec7e650e4144b0413f3eb258131e39
BLAKE2b-256 3b29147031f6d76fc882f6cd973e6acf6c25634a388d9247ad3f4dd04fd1ea7a

See more details on using hashes here.

File details

Details for the file iflow_mcp_arxiv_mcp_server-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for iflow_mcp_arxiv_mcp_server-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c51a87e3298e6bc93fab68b5cbf11648d53e4dde3fb0b382316aa7af67dba9d7
MD5 f9deec761013e5b15e9048ec4a10ad7f
BLAKE2b-256 c7ce9d69965fd58add8e538f415f0bb79656395b486cb79b2b457fbead591540

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page