Preprint Fulltext

Overview

Preprint Fulltext is a Model Context Protocol server that retrieves bioRxiv, medRxiv, and arXiv preprints as structured sections, enabling AI agents to search and analyze research papers programmatically. It parses full-text preprints into organized sections suitable for language model processing and semantic search across preprint repositories.

The server runs locally as a Python package installed via uvx preprint-fulltext and communicates over stdio using the MCP protocol. It requires an API key for authentication and is currently at release v0.1.0. The source code is available at genecell/preprint-fulltext on GitHub under topics including ai-for-science, arxiv, bioinformatics, biorxiv, europepmc, jats, and llm.

Preprint Fulltext is listed in the AI & Agents category on mcp.site and works with all MCP-compatible clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim your listing to verify ownership and keep the information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "preprint_fulltext": {
      "command": "uvx",
      "args": [
        "preprint-fulltext"
      ]
    }
  }
}