Skip to main content
Glama

search_semantic_scholar

Search academic papers on Semantic Scholar with citation data, year filters, and field-of-study options to find relevant research publications.

Instructions

Search Semantic Scholar for academic papers with citation data

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query string
maxResultsNoMaximum number of results to return
yearNoYear filter (e.g., "2023", "2020-2023")
fieldsOfStudyNoFields of study filter (e.g., ["Computer Science", "Biology"])

Implementation Reference

  • Core implementation of the search functionality using Semantic Scholar Graph API v1, including query parameterization, API rate limiting, error handling, and result parsing into Paper objects.
    async search(query: string, options: SemanticSearchOptions = {}): Promise<Paper[]> { await this.rateLimiter.waitForPermission(); try { const params: Record<string, any> = { query: query, limit: Math.min(options.maxResults || 10, 100), // API限制最大100 fields: [ 'paperId', 'title', 'abstract', 'venue', 'year', 'referenceCount', 'citationCount', 'influentialCitationCount', 'isOpenAccess', 'openAccessPdf', 'fieldsOfStudy', 's2FieldsOfStudy', 'publicationTypes', 'publicationDate', 'journal', 'authors', 'externalIds', 'url' ].join(',') }; // 添加年份过滤 if (options.year) { params.year = options.year; } // 添加研究领域过滤 if (options.fieldsOfStudy && options.fieldsOfStudy.length > 0) { params.fieldsOfStudy = options.fieldsOfStudy.join(','); } const url = `${this.baseApiUrl}/paper/search`; const headers: Record<string, string> = { 'User-Agent': USER_AGENT, 'Accept': 'application/json', 'Accept-Language': 'en-US,en;q=0.9' }; // 添加API密钥(如果有)- 根据官方文档推荐的方式 if (this.apiKey) { headers['x-api-key'] = this.apiKey; } logDebug(`Semantic Scholar API Request: GET ${url}`); logDebug('Semantic Scholar Request params:', params); const response = await axios.get(url, { params, headers, timeout: TIMEOUTS.DEFAULT, // 改善请求可靠性 maxRedirects: 5, validateStatus: (status) => status < 500 // allow 4xx through so we can provide consistent messaging }); logDebug(`Semantic Scholar API Response: ${response.status} ${response.statusText}`); // 处理可能的错误响应 if (response.status >= 400) { // Convert non-throwing 4xx response to unified error handling this.handleHttpError({ response, config: response.config }, 'search'); } const papers = this.parseSearchResponse(response.data); logDebug(`Semantic Scholar Parsed ${papers.length} papers`); return papers; } catch (error: any) { logDebug('Semantic Scholar Search Error:', error.message); // 处理速率限制错误 if (error.response?.status === 429) { const retryAfter = error.response.headers['retry-after']; logDebug( `Rate limited by Semantic Scholar API. ${retryAfter ? `Retry after ${retryAfter} seconds.` : 'Please wait before making more requests.'}` ); } // 处理API限制错误 if (error.response?.status === 403) { logDebug('Access denied. Please check your API key or ensure you are within the free tier limits.'); } this.handleHttpError(error, 'search'); } }
  • MCP tool call handler case that delegates to the SemanticScholarSearcher instance and formats the response with rate limit information.
    case 'search_semantic_scholar': { const { query, maxResults, year, fieldsOfStudy } = args; const results = await searchers.semantic.search(query, { maxResults, year, fieldsOfStudy }); const rateStatus = searchers.semantic.getRateLimiterStatus(); const apiKeyStatus = searchers.semantic.hasApiKey() ? 'configured' : 'not configured (using free tier)'; const rateLimit = searchers.semantic.hasApiKey() ? '200 requests/minute' : '20 requests/minute'; return jsonTextResponse( `Found ${results.length} Semantic Scholar papers.\n\nAPI Status: ${apiKeyStatus} (${rateLimit})\nRate Limiter: ${rateStatus.availableTokens}/${rateStatus.maxTokens} tokens available\n\n${JSON.stringify( results.map((paper: Paper) => PaperFactory.toDict(paper)), null, 2 )}` ); }
  • Zod schema for validating input arguments to the search_semantic_scholar tool.
    export const SearchSemanticScholarSchema = z .object({ query: z.string().min(1), maxResults: z.number().int().min(1).max(100).optional().default(10), year: z.string().optional(), fieldsOfStudy: z.array(z.string()).optional() }) .strip();
  • Tool registration definition including name, description, and JSON input schema, added to the TOOLS array for MCP.
    { name: 'search_semantic_scholar', description: 'Search Semantic Scholar for academic papers with citation data', inputSchema: { type: 'object', properties: { query: { type: 'string', description: 'Search query string' }, maxResults: { type: 'number', minimum: 1, maximum: 100, description: 'Maximum number of results to return' }, year: { type: 'string', description: 'Year filter (e.g., "2023", "2020-2023")' }, fieldsOfStudy: { type: 'array', items: { type: 'string' }, description: 'Fields of study filter (e.g., ["Computer Science", "Biology"])' } }, required: ['query'] } },
  • Instantiation of the SemanticScholarSearcher instance, configured with optional API key from environment, and added to the searchers object.
    const semanticSearcher = new SemanticScholarSearcher(process.env.SEMANTIC_SCHOLAR_API_KEY);

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/Dianel555/paper-search-mcp-nodejs'

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