ArXiv MCP Server

Name: ArXiv MCP Server
Author: MCP-Mirror

@MCP-Mirror

Repository

About ArXiv MCP Server

Mirror of

#arxiv #mcp #ai-assistant

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "blazickjp_arxiv-mcp-server": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "git+https://github.com/blazickjp/arxiv-mcp-server.git"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is ArXiv MCP Server?

The ArXiv MCP Server provides a bridge between AI assistants and arXiv’s research repository through the Message Control Protocol (MCP). It allows AI models to search for papers and access their content programmatically, designed for developers integrating AI tools with scientific literature.

How to use ArXiv MCP Server?

Install the server using uv pip install git+https://github.com/blazickjp/arxiv-mcp-server.git. Configure it in your MCP client config file with the command uv run arxiv-mcp-server --storage-path /path/to/paper/storage. The server exposes four tools: search_papers, download_paper, list_papers, and read_paper, which can be called from your AI assistant.

Key features of ArXiv MCP Server

Search arXiv papers with filters for date ranges and categories
Download papers by arXiv ID for offline access
List all previously downloaded papers in one view
Read full content of stored papers locally
Papers saved locally for faster repeated access

Use cases of ArXiv MCP Server

AI assistant queries recent machine learning papers using date and category filters
Researcher downloads and reads arXiv papers without leaving the chat interface
Automated paper collection using specific arXiv IDs for literature reviews
Building a local cache of papers for offline or low-latency retrieval

FAQ from ArXiv MCP Server

What is the ArXiv MCP Server used for?

It enables AI assistants to search, download, list, and read arXiv papers through the MCP protocol, acting as a bridge between language models and the arXiv repository.

How do I install the ArXiv MCP Server?

Install it using the uv package manager: uv pip install git+https://github.com/blazickjp/arxiv-mcp-server.git. A virtual environment and Python 3.11 or higher are required.

What tools does the server provide?

The server offers four tools: search_papers (query with filters), download_paper (by arXiv ID), list_papers (view downloaded papers), and read_paper (access paper content).

How do I configure the storage path for papers?

Set the --storage-path argument when running the server, or use the ARXIV_STORAGE_PATH environment variable. The default location is ~/.arxiv-mcp-server/papers.

What are the runtime dependencies?

Python 3.11+ is required, and the server is installed via uv. No other runtime dependencies are mentioned beyond those resolved by the package manager.