Skip to main content
Glama

search_papers

Search for cryptographic research papers in the IACR Cryptology ePrint Archive by query, year, or category, and retrieve relevant results programmatically.

Instructions

Search for papers in the IACR Cryptology ePrint Archive

Input Schema

NameRequiredDescriptionDefault
categoryNo
max_resultsNo
queryYes
yearNo

Input Schema (JSON Schema)

{ "properties": { "category": { "type": "string" }, "max_results": { "default": 20, "type": "number" }, "query": { "type": "string" }, "year": { "type": "number" } }, "required": [ "query" ], "type": "object" }

Implementation Reference

  • The main handler function that implements the search_papers tool: validates args, fetches IACR ePrint RSS feed, parses XML, filters papers by query, optional year/category/max_results, returns JSON list of matching papers.
    private async searchPapers(args: unknown) { const validatedArgs = SearchPapersSchema.parse(args); try { // Fetch RSS feed with comprehensive headers const response = await axios.get(IACR_RSS_URL, { headers: { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36', 'Accept': 'application/xml,text/xml,*/*;q=0.8', 'Accept-Language': 'en-US,en;q=0.9' }, timeout: 15000 }); // Parse XML feed const parsedFeed = await parseStringPromise(response.data); // Ensure items exist if (!parsedFeed.rss?.channel?.[0]?.item) { console.error('No items found in RSS feed'); return { content: [{ type: 'text', text: '[]' }] }; } // Current year for filtering const currentYear = new Date().getFullYear(); // Extract and filter papers const papers = parsedFeed.rss.channel[0].item .map((item: any) => ({ id: item.link[0].split('/').pop(), title: item.title[0], authors: item['dc:creator'] ? item['dc:creator'][0] : 'Unknown', link: item.link[0], description: item.description[0], pubDate: item.pubDate[0] })) .filter((paper: IACRPaper) => { const title = paper.title.toLowerCase(); const description = paper.description.toLowerCase(); const query = validatedArgs.query.toLowerCase(); // Query matching const matchesQuery = title.includes(query) || description.includes(query); // Year filtering const paperYear = new Date(paper.pubDate).getFullYear(); const matchesYear = !validatedArgs.year || (validatedArgs.year && paperYear === validatedArgs.year) || (paperYear >= currentYear - 10); return matchesQuery && matchesYear; }) .slice(0, validatedArgs.max_results) .map((paper: IACRPaper) => ({ id: paper.id, title: paper.title, authors: paper.authors, year: new Date(paper.pubDate).getFullYear(), link: paper.link, abstract: paper.description })); // Log results for debugging console.error('Search Results:', JSON.stringify(papers, null, 2)); return { content: [{ type: 'text', text: JSON.stringify(papers, null, 2) }] }; } catch (error) { // Comprehensive error logging console.error('Search Error:', error); throw new McpError( ErrorCode.InternalError, `Search failed: ${error instanceof Error ? error.message : 'Unknown error'}` ); } }
  • Zod schema defining the input parameters for search_papers: query (required string), optional year (number), category (string), max_results (number, default 20).
    const SearchPapersSchema = z.object({ query: z.string(), year: z.number().optional(), category: z.string().optional(), max_results: z.number().optional().default(20) });
  • src/index.ts:67-80 (registration)
    Tool registration in the listTools handler: defines name, description, and inputSchema for search_papers.
    { name: 'search_papers', description: 'Search for papers in the IACR Cryptology ePrint Archive', inputSchema: { type: 'object', properties: { query: { type: 'string' }, year: { type: 'number' }, category: { type: 'string' }, max_results: { type: 'number', default: 20 } }, required: ['query'] } },

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/doomdagadiggiedahdah/iacr-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server