drio
Open app

paperscraper-MCP-Server

Source

A MCP Server for paperscraper：Tools to scrape publication metadata from pubmed, arxiv, medrxiv, biorxiv and chemrxiv.

Catalog onlyCatalog onlySTDIO

Overview

paperscraper-MCP-Server is a tool designed to scrape publication metadata from various scientific repositories including PubMed, arXiv, medRxiv, bioRxiv, and chemRxiv.

To use paperscraper-MCP-Server, set up the server and utilize its API to request metadata for specific publications by providing the relevant identifiers or search queries.

  • Scrapes metadata from multiple scientific databases - Supports various publication types and formats - Easy integration with other research tools and workflows
  1. Collecting publication data for systematic reviews
  2. Automating the extraction of citation information for research papers
  3. Enhancing bibliographic databases with up-to-date metadata

Add to your AI client

Use these steps to connect paperscraper-MCP-Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "paperscraper-mcp-server-jackkuo666": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-paperscraper-mcp-server-jackkuo666"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "paperscraper-mcp-server-jackkuo666": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-paperscraper-mcp-server-jackkuo666"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "paperscraper-mcp-server-jackkuo666": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-paperscraper-mcp-server-jackkuo666"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "paperscraper-mcp-server-jackkuo666": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-paperscraper-mcp-server-jackkuo666"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "paperscraper-mcp-server-jackkuo666": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-paperscraper-mcp-server-jackkuo666"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "paperscraper-mcp-server-jackkuo666": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-paperscraper-mcp-server-jackkuo666"
      ]
    }
  }
}

FAQ

What databases does paperscraper-MCP-Server support?

It supports PubMed, arXiv, medRxiv, bioRxiv, and chemRxiv.

Is there a limit to the number of requests I can make?

The server may have rate limits depending on the configuration and usage policies.

Can I customize the metadata fields I want to scrape?

Yes, you can specify which metadata fields to retrieve based on your needs.

Research and data