Skip to main content
Glama

Search Papers by Keyword

search_papers_by_keyword

Find academic papers by entering keywords, with options to sort by publication year or citation count for targeted research discovery.

Instructions

Search academic papers by keyword

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordYesSearch keyword
pageNoPage number, starting from 0
sizeNoNumber of papers per page, maximum 10
orderNoSort order: year (by publication year) or n_citation (by citation count)

Implementation Reference

  • src/index.ts:35-71 (registration)
    Registration of the MCP tool 'search_papers_by_keyword' including schema and inline handler that delegates to AminerClient
    server.registerTool(
      "search_papers_by_keyword",
      {
        title: "Search Papers by Keyword",
        description: "Search academic papers by keyword",
        inputSchema: {
          keyword: z.string().describe("Search keyword"),
          page: z.number().min(0).default(0).describe("Page number, starting from 0"),
          size: z.number().min(1).max(10).default(10).describe("Number of papers per page, maximum 10"),
          order: z.enum(["year", "n_citation"]).optional().describe("Sort order: year (by publication year) or n_citation (by citation count)")
        }
      },
      async ({ keyword, page, size, order }) => {
        try {
          const result = await aminerClient.searchByKeyword(keyword, page, size, order);
          const formattedResult = aminerClient.formatSearchResults(result);
          
          return {
            content: [{
              type: "text",
              text: JSON.stringify(formattedResult, null, 2)
            }]
          };
        } catch (error) {
          return {
            content: [{
              type: "text",
              text: JSON.stringify({
                error: "Search failed",
                message: error instanceof Error ? error.message : 'Unknown error'
              }, null, 2)
            }],
            isError: true
          };
        }
      }
    );
  • Core handler logic for searching papers via AMiner API in AminerClient.searchPapers, called by searchByKeyword
    async searchPapers(params: SearchParams): Promise<SearchResult> {
      // Validate required parameters
      if (!params.keyword && !params.venue && !params.author) {
        throw new Error('At least one of keyword, venue, or author must be provided');
      }
    
      if (params.size > 10) {
        throw new Error('Size parameter cannot exceed 10');
      }
    
      // Build query parameters
      const searchParams = new URLSearchParams();
      if (params.keyword) searchParams.append('keyword', params.keyword);
      if (params.venue) searchParams.append('venue', params.venue);
      if (params.author) searchParams.append('author', params.author);
      searchParams.append('page', params.page.toString());
      searchParams.append('size', params.size.toString());
      if (params.order) searchParams.append('order', params.order);
    
      const url = `${this.config.baseUrl}?${searchParams.toString()}`;
    
      try {
        const response = await fetch(url, {
          method: 'GET',
          headers: {
            'Authorization': this.config.apiKey,
            'Content-Type': 'application/json',
          },
        });
    
        if (!response.ok) {
          throw new Error(`HTTP ${response.status}: ${response.statusText}`);
        }
    
        const data = await response.json() as AminerSearchResponse;
    
        // Add detailed response data check
        if (!data) {
          throw new Error('API returned empty response');
        }
    
        if (!data.success) {
          throw new Error(`API Error (${data.code}): ${data.msg}`);
        }
    
        // Check the completeness of the response data
        if (typeof data.total !== 'number') {
          console.warn('API response missing or invalid total field, defaulting to 0');
        }
    
        // Ensure data.data is not null, if it is null, use an empty array
        const papers = data.data || [];
        const total = data.total || 0;
    
        return {
          papers,
          total,
          page: params.page,
          size: params.size,
          hasMore: (params.page + 1) * params.size < total,
        };
      } catch (error) {
        if (error instanceof Error) {
          throw new Error(`Failed to search papers: ${error.message}`);
        }
        throw new Error('Unknown error occurred while searching papers');
      }
    }
  • Wrapper method searchByKeyword that invokes the core searchPapers with keyword parameter
    async searchByKeyword(keyword: string, page = 0, size = 10, order?: 'year' | 'n_citation'): Promise<SearchResult> {
      return this.searchPapers({ keyword, page, size, order });
    }
  • Helper function to format raw search results into structured JSON output used by the tool handler
    formatSearchResults(result: SearchResult): SearchResultFormatted {
      const { papers, total, page, size, hasMore } = result;
      
      // Ensure papers is not null or undefined
      const formattedPapers = papers && Array.isArray(papers) 
        ? papers.map((paper, index) => {
            const formattedPaper = this.formatPaper(paper);
            // Only process successfully formatted papers, skip error results
            if ('error' in formattedPaper) {
              return null;
            }
            return {
              index: page * size + index + 1,
              ...formattedPaper
            };
          }).filter((paper): paper is NonNullable<typeof paper> => paper !== null)
        : [];
    
      return {
        summary: {
          total,
          page: page + 1,
          size,
          hasMore,
          currentPageResults: formattedPapers.length
        },
        papers: formattedPapers,
        pagination: {
          currentPage: page + 1,
          nextPage: hasMore ? page + 2 : null,
          previousPage: page > 0 ? page : null
        }
      };
    }
  • Zod input schema definition for the search_papers_by_keyword tool parameters
    inputSchema: {
      keyword: z.string().describe("Search keyword"),
      page: z.number().min(0).default(0).describe("Page number, starting from 0"),
      size: z.number().min(1).max(10).default(10).describe("Number of papers per page, maximum 10"),
      order: z.enum(["year", "n_citation"]).optional().describe("Sort order: year (by publication year) or n_citation (by citation count)")
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the basic action ('Search academic papers by keyword') without mentioning pagination behavior, rate limits, authentication requirements, error handling, or what the search results might look like. For a search tool with no annotation coverage, this leaves significant gaps in understanding its operational behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with just one sentence ('Search academic papers by keyword'), which is front-loaded and wastes no words. Every part of the sentence directly contributes to understanding the tool's purpose, making it efficiently structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (a search function with 4 parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't address key contextual aspects like result format, pagination details, search scope, or how it differs from sibling tools, leaving the agent with insufficient information to use it effectively beyond the basic schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with clear documentation for all parameters (keyword, page, size, order). The description doesn't add any meaningful parameter semantics beyond what's already in the schema, such as explaining search relevance, keyword matching logic, or default sorting. With high schema coverage, the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as 'Search academic papers by keyword', which includes a specific verb ('Search') and resource ('academic papers') with the method ('by keyword'). However, it doesn't differentiate from sibling tools like search_papers_by_author or search_papers_by_venue, which would require explicit comparison to achieve a score of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With sibling tools like search_papers_advanced, search_papers_by_author, and search_papers_by_venue available, there's no indication of when this keyword-based search is preferred or what its limitations are compared to more advanced or specific searches.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other 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/scipenai/aminer-mcp-server'

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