Arxiv

APR papers/APR MCP

python

2

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "wr-web-apr": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "arxiv-mcp-server",
        "--storage-path",
        "/path/to/paper/storage"
      ],
      "env": {
        "ARXIV_STORAGE_PATH": "/path/to/paper/storage"
      }
    }
  }
}

You can enable AI assistants to search, download, and read arXiv papers through a compact MCP server. It acts as a bridge between your AI client and arXiv, letting you discover papers, fetch their content, and manage a local storage of downloaded papers for fast access.

How to use

Connect your MCP client to the arXiv MCP Server and use the four core capabilities to work with papers. Start by searching for papers with keywords, date ranges, and categories. Then download papers you want to inspect, list what you already have stored locally, and read the content of any downloaded paper. All actions happen through the MCP interface, so you can orchestrate these steps inside your AI workflow without leaving your assistant.

Practical usage patterns include: searching for recent papers on a topic, downloading a handful of relevant papers for offline reading, listing your local collection to confirm what you have, and reading a paper’s content to extract summaries or figures. The server saves papers locally for quick reuse, and you can retrigger downloads or reads as part of larger research prompts.

How to install

Prerequisites: you need a runtime that can execute MCP server tools. In this setup, you will use the uv runtime to install and run the server locally.

Step 1: Install the MCP server locally using uv

Step 2: Enable development mode if you are contributing or debugging

Step 3: Run the server with a configured storage path so papers are saved locally

Configuration and startup

Configure the MCP client to connect to the arXiv MCP Server by adding an MCP server entry in your client configuration. The server stores downloaded papers under a storage path you specify.

Additional notes

Environment variable ARXIV_STORAGE_PATH defines where papers are stored locally. Use a path you control and ensure the directory exists and is writable by the process running the MCP server.

Available tools

search_papers

Query arXiv papers with optional filters such as query text, date range, and categories.

download_paper

Download a paper by its arXiv ID and save it to local storage.

list_papers

List all papers that have been downloaded and are stored locally.

read_paper

Read and return the content of a downloaded paper by its arXiv ID.

deep-paper-analysis

Prompts-based workflow to analyze a paper by its ID, coordinating available tools to produce a structured analysis.