Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@IACR MCP Server search for recent papers on post-quantum cryptography"
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.
This Model Context Protocol (MCP) server provides a programmatic interface to the IACR Cryptology ePrint Archive, enabling efficient retrieval of cryptographic research papers.
Related MCP server: All-in-MCP
🔍 Search cryptographic papers
📋 Retrieve paper metadata
🔒 Secure access to research publications
Node.js (v16+)
npm or yarn
To install IACR Cryptology ePrint Archive for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install iacr-mcp-server --client claudegit clone https://github.com/yourusername/iacr-mcp-server.git
cd iacr-mcp-server
npm installNo additional configuration is required. The server uses the IACR ePrint Archive's RSS feed for data retrieval.
search_papers: Search for papers
Parameters:
query: Search term (required)
year: Publication year (optional)
max_results: Maximum number of results (default: 20)
get_paper_details: Retrieve details for a specific paper
Parameters:
paper_id: Unique paper identifier (required)
Fork the repository
Create a feature branch
Commit your changes
Push to the branch
Create a Pull Request
This is an unofficial tool. Always refer to the original IACR Cryptology ePrint Archive for the most accurate and up-to-date research publications.
For issues, questions, or suggestions, please open a GitHub issue.
Download a paper in PDF or TXT format
Inputs: paper_id (required), format.
Retrieve details of a specific paper by its ID
Inputs: paper_id (required).
Search for papers in the IACR Cryptology ePrint Archive
Inputs: query (required), category, max_results, year.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct purpose: download_paper retrieves files, get_paper_details fetches metadata, and search_papers finds papers. There is no overlap in functionality, making it easy for an agent to select the correct tool without confusion.
All tool names follow a consistent verb_noun pattern (download_paper, get_paper_details, search_papers) with clear, descriptive verbs. There are no deviations in naming conventions, ensuring predictability and readability.
With only 3 tools, the server feels thin for a paper archive domain, as it lacks operations like filtering, listing categories, or updating metadata. While the core functions are covered, the count is borderline minimal for typical agent workflows.
The tools cover essential CRUD-like operations: search (read), get details (read), and download (retrieve). However, there are minor gaps, such as no ability to list papers by year or category, which agents might need to work around for more complex queries.
Authenticated public evidence search, verification, research jobs, exports, and webhooks.
Pay-per-call x402 arXiv paper search, metadata, abstracts, and category listings.
License-checked research archive and technical-spec search for AI agents. Pay per call via x402.
IEEE Xplore MCP — BYOK wrapper over the IEEE Xplore Metadata Search API…
