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.
@MCP-Mirror
Basic information
Mirror of
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"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
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.
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.
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.
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).
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`.
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.

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can

17 tools for marketing and SEO research inside Claude Code, Cursor, Codex or ChatGPT: the ads any domain runs on Meta and Google, how a product grew from 12 public sources with every claim linked, your own Search Console

Connect your AI to millions of laws and court cases! Lawstronaut is the infrastructure layer that connects AI agents and software to millions of legal documents across 150+ jurisdictions, structured legal data, continuou
The only MCP server with live whale trades across 15 exchanges plus on-chain DEX flow. Smart Money Radar, real liquidations and outcome-scored signals. No API key required.
Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl
Comments