Which integrations are available for this server?

Exposes tools for searching arXiv for academic papers, retrieving full-text content in HTML format via ar5iv, and downloading papers as PDFs.

How do I use arxiv-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@arxiv-mcp find recent papers about large language model reasoning" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

arxiv-mcp

License: MIT

An MCP server that exposes arXiv paper search, full-text HTML retrieval, and PDF download as tools. Built with FastMCP and served over SSE.

Tools

Tool	Description
`search_papers`	Search arXiv for papers matching a query. Returns titles, authors, abstracts, and links.
`get_paper_html`	Retrieve the full text of an arXiv paper as HTML via ar5iv.
`download_pdf`	Download an arXiv paper as PDF to a specified directory (default: `./downloads`).

Quickstart

Requires Python 3.13+ and uv.

uv sync
uv run arxiv-mcp

The server starts on http://0.0.0.0:8613.

Options

Flag	Description	Default
`--port`	Port to listen on	`8613`
`--output-dir`	Default PDF download directory	`./downloads`

uv run arxiv-mcp --port 9000 --output-dir /tmp/papers

The output_dir parameter on the download_pdf tool overrides the server default when provided.

Docker Compose

docker compose up --build

Downloads are persisted to ./downloads on the host via a bind mount.

MCP client configuration

Add the server to your MCP client config:

{
  "mcpServers": {
    "arxiv": {
      "url": "http://localhost:8613/sse"
    }
  }
}

Development

uv sync                  # Install dependencies (including dev)
uv run pytest            # Run tests
uv run ruff check        # Lint
uv run ruff format       # Format
uv run pyright           # Type check

Architecture

src/arxiv_mcp/
  domain.py   - Pydantic models (Paper)
  client.py   - arXiv API wrapper (search, HTML via ar5iv, PDF download)
  server.py   - FastMCP server exposing the three tools