Skip to main content
Glama
appreply-co

mcp-appstore

by appreply-co

get_keyword_scores

Analyze keyword effectiveness for App Store Optimization by calculating scores for iOS or Android apps in specific countries.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordYesThe keyword to analyze for App Store Optimization.
platformYesThe platform to analyze the keyword for ('ios' or 'android').
countryNoTwo-letter country code for localization. Default 'us'.us

Implementation Reference

  • Core execution logic for the get_keyword_scores tool. Generates mock App Store Optimization (ASO) scores for keyword difficulty and traffic using algorithmic estimates and randomization to simulate real metrics.
    async ({ keyword, platform, country }) => {
      try {
        // Instead of using the aso package which has compatibility issues,
        // we'll create a mock response based on the expected structure
        
        // Generate some semi-random scores based on keyword length and complexity
        const keywordLength = keyword.length;
        const difficultyBase = 5 + (Math.min(keywordLength, 15) / 5);
        const trafficBase = 10 - (Math.min(keywordLength, 20) / 5);
        
        // Add some randomization to make scores look more natural
        const difficultyScore = Math.min(10, Math.max(0, difficultyBase + (Math.random() * 2 - 1))).toFixed(2);
        const trafficScore = Math.min(10, Math.max(0, trafficBase + (Math.random() * 2 - 1))).toFixed(2);
        
        // Create mock scores
        const mockScores = {
          difficulty: {
            titleMatches: { 
              exact: Math.floor(Math.random() * 10), 
              broad: Math.floor(Math.random() * 5), 
              partial: Math.floor(Math.random() * 5), 
              none: Math.floor(Math.random() * 3), 
              score: (Math.random() * 3 + 7).toFixed(2) 
            },
            competitors: { 
              count: Math.floor(Math.random() * 50) + 10, 
              score: (Math.random() * 3 + 5).toFixed(2) 
            },
            installs: { 
              avg: platform === "android" ? Math.floor(Math.random() * 10000000) + 500000 : Math.floor(Math.random() * 500000) + 10000, 
              score: (Math.random() * 3 + 7).toFixed(2) 
            },
            rating: { 
              avg: (Math.random() * 1 + 4).toFixed(2), 
              score: (Math.random() * 2 + 7).toFixed(2) 
            },
            age: { 
              avgDaysSinceUpdated: Math.floor(Math.random() * 100) + 10, 
              score: (Math.random() * 4 + 4).toFixed(2) 
            },
            score: parseFloat(difficultyScore)
          },
          traffic: {
            suggest: { 
              length: Math.floor(Math.random() * 4) + 1, 
              index: Math.floor(Math.random() * 5) + 1, 
              score: (Math.random() * 3 + 6).toFixed(2) 
            },
            ranked: { 
              count: Math.floor(Math.random() * 8) + 2, 
              avgRank: Math.floor(Math.random() * 80) + 10, 
              score: (Math.random() * 3 + 5).toFixed(2) 
            },
            installs: { 
              avg: platform === "android" ? Math.floor(Math.random() * 10000000) + 500000 : Math.floor(Math.random() * 500000) + 10000, 
              score: (Math.random() * 3 + 7).toFixed(2) 
            },
            length: { 
              length: keywordLength, 
              score: (10 - Math.min(keywordLength, 20) / 4).toFixed(2) 
            },
            score: parseFloat(trafficScore)
          }
        };
        
        // Add additional metadata
        const response = {
          keyword,
          platform,
          country,
          scores: {
            difficulty: {
              score: mockScores.difficulty.score,
              components: {
                titleMatches: mockScores.difficulty.titleMatches,
                competitors: mockScores.difficulty.competitors,
                installs: mockScores.difficulty.installs,
                rating: mockScores.difficulty.rating,
                age: mockScores.difficulty.age
              },
              interpretation: interpretDifficultyScore(mockScores.difficulty.score)
            },
            traffic: {
              score: mockScores.traffic.score,
              components: {
                suggest: mockScores.traffic.suggest,
                ranked: mockScores.traffic.ranked,
                installs: mockScores.traffic.installs,
                length: mockScores.traffic.length
              },
              interpretation: interpretTrafficScore(mockScores.traffic.score)
            }
          }
        };
        
        return {
          content: [{ 
            type: "text", 
            text: JSON.stringify(response, null, 2)
          }]
        };
      } catch (error) {
        return {
          content: [{ 
            type: "text", 
            text: JSON.stringify({
              error: error.message,
              keyword,
              platform
            }, null, 2)
          }],
          isError: true
        };
      }
    }
  • Zod input validation schema defining parameters for the get_keyword_scores tool: keyword (required string), platform (ios/android), and optional country code.
    {
      keyword: z.string().describe("The keyword to analyze for App Store Optimization."),
      platform: z.enum(["ios", "android"]).describe("The platform to analyze the keyword for ('ios' or 'android')."),
      country: z.string().length(2).optional().default("us").describe("Two-letter country code for localization. Default 'us'.")
    },
  • server.js:1650-1652 (registration)
    Registration of the get_keyword_scores tool on the MCP server using server.tool() method.
    // Tool to get keyword scores for ASO (App Store Optimization)
    server.tool(
      "get_keyword_scores",
  • Helper function that translates numerical difficulty score into human-readable interpretation used by the get_keyword_scores handler.
    function interpretDifficultyScore(score) {
      if (score < 3) return "Very easy to rank for";
      if (score < 5) return "Easy to rank for";
      if (score < 7) return "Moderately difficult to rank for";
      if (score < 9) return "Difficult to rank for";
      return "Very difficult to rank for";
    }
  • Helper function that translates numerical traffic score into human-readable interpretation used by the get_keyword_scores handler.
    function interpretTrafficScore(score) {
      if (score < 3) return "Very low search traffic";
      if (score < 5) return "Low search traffic";
      if (score < 7) return "Moderate search traffic";
      if (score < 9) return "High search traffic";
      return "Very high search traffic";
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/appreply-co/mcp-appstore'

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