Skip to main content
Glama
eprint-mcp-server

eprint-mcp-server

by heewon-chung

IACR ePrint Archive MCP Server

License: MIT Node.js TypeScript

A Model Context Protocol (MCP) server that provides access to the IACR Cryptology ePrint Archive, enabling AI assistants to search and retrieve cryptographic research papers.

โœจ Features

  • ๐Ÿ” Smart Search: Search papers by title, abstract, author, or keywords (RSS-based filtering)

  • ๐Ÿ“„ Paper Details: Get comprehensive information about specific papers

  • ๐Ÿ“ฐ Recent Papers: Retrieve the latest published papers from RSS feed

  • ๐Ÿ”— Direct Links: Get web page and PDF URLs for papers

  • ๐Ÿ“‹ Download Info: Get download information for paper PDFs

  • ๐Ÿ”’ Privacy Focused: No cookies, no tracking, respects ePrint Archive guidelines

Related MCP server: ArXiv MCP Server

๐Ÿš€ Quick Start

Installation

Option 1: Direct Installation

# Clone the repository
git clone https://github.com/YOUR_USERNAME/eprint-mcp-server.git
cd eprint-mcp-server

# Install dependencies and build
npm install
npm run build

Option 2: Using npx (Coming Soon)

npx eprint-mcp-server

Claude Desktop Setup

  1. Find your Claude Desktop config file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

  2. Add the server configuration:

    {
      "mcpServers": {
        "eprint": {
          "command": "node",
          "args": ["/path/to/eprint-mcp-server/dist/index.js"]
        }
      }
    }
  3. Restart Claude Desktop completely (โŒ˜+Q then reopen)

๐Ÿ“– Usage Examples

Search Papers

Find papers about "zero knowledge proofs"

Get Recent Papers

Show me the 10 most recent cryptography papers

Get Paper Details

Tell me about paper 2025/123

Find by Author

Find papers by Goldreich from 2024

๐Ÿ› ๏ธ Development

Prerequisites

  • Node.js 18.0.0 or higher

  • npm or yarn

Setup

git clone https://github.com/YOUR_USERNAME/eprint-mcp-server.git
cd eprint-mcp-server
npm install

Development Commands

# Development with hot reload
npm run dev

# Build for production
npm run build

# Run tests
npm test

# Type checking
npm run type-check

Project Structure

eprint-mcp-server/
โ”œโ”€โ”€ src/
โ”‚   โ”œโ”€โ”€ index.ts          # Main MCP server
โ”‚   โ”œโ”€โ”€ eprintClient.ts   # ePrint Archive API client
โ”‚   โ””โ”€โ”€ types.ts          # TypeScript type definitions
โ”œโ”€โ”€ dist/                 # Compiled JavaScript output
โ”œโ”€โ”€ tests/               # Test files
โ”œโ”€โ”€ package.json
โ””โ”€โ”€ README.md

๐Ÿ”ง Configuration

Environment Variables

  • DEBUG: Set to 1 to enable debug logging

  • MAX_RESULTS: Maximum number of search results (default: 100)

MCP Server Options

{
  "mcpServers": {
    "eprint": {
      "command": "node",
      "args": ["./dist/index.js"],
      "env": {
        "DEBUG": "0",
        "MAX_RESULTS": "50"
      }
    }
  }
}

๐Ÿ“š Available Tools

Tool

Description

Parameters

search_papers

Search for papers

query, maxResults, author, dateFrom, dateTo

get_paper

Get paper details

paperId

get_recent_papers

Get recent papers

limit

download_paper

Get download info

paperId, outputPath

get_paper_url

Get paper URLs

paperId

๐Ÿ” Search Limitations

Currently, the ePrint Archive's search API endpoint is not publicly available, so this server uses RSS feed filtering for search functionality. This means:

  • โœ… Search works within recent papers (last ~100 papers from RSS)

  • โš ๏ธ Historical search is limited

  • ๐Ÿ”„ We're working on implementing full search capabilities

๐Ÿค Contributing

  1. Fork the repository

  2. Create a feature branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add amazing feature')

  4. Push to the branch (git push origin feature/amazing-feature)

  5. Open a Pull Request

๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

๐Ÿ™ Acknowledgments

๐Ÿ“ž Support

๐Ÿ”„ Changelog

v1.0.0 (2025-06-25)

  • โœจ Initial release

  • ๐Ÿ” RSS-based search functionality

  • ๐Ÿ“„ Paper details retrieval

  • ๐Ÿ“ฐ Recent papers listing

  • ๐Ÿ”— Direct URL generation


Made with โค๏ธ for the cryptography research community

Available Tools

5 tools
download_paperC

Download a paper PDF (returns download information)

Inputs: paperId (required), outputPath.

get_paperB

Get detailed information about a specific paper by ID

Inputs: paperId (required).

get_paper_urlB

Get direct URLs for a paper (web page and PDF)

Inputs: paperId (required).

get_recent_papersB

Get the most recently published papers

Inputs: limit.

search_papersB

Search for papers in the IACR ePrint Archive

Inputs: query (required), author, dateTo, sortBy, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    A3.5/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: searching, getting details, getting URLs, downloading, and listing recent papers. No overlap.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with underscores (e.g., download_paper, search_papers). The naming is uniform and predictable.

    Tool Count5/5

    With 5 tools, the server is well-scoped for its domain. It provides essential operations without being too few or overly numerous.

    Completeness4/5

    The tool set covers search, metadata retrieval, URL access, and download. Minor gap: lack of explicit filtering by author or category, but search likely supports parameters.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to search and access arXiv research papers through a simple Message Control Protocol interface, allowing for paper search, download, listing, and reading capabilities.
      4
      7
      Apache 2.0
    • A
      license
      B
      quality
      Not graded
      maintenance
      Enables AI assistants to search and retrieve academic papers from arXiv through MCP tools, supporting search by various criteria, detailed paper information, category browsing, and PDF content extraction.
      4
      79 npm
      2
      -
    • A
      license
      B
      quality
      D
      maintenance
      Enables searching, retrieving, and parsing academic papers from arXiv, including keyword search, PDF downloads, content extraction from HTML/PDF formats, and accessing the latest AI research papers.
      4
      8 npm
      MIT