Skip to main content
Glama
0xGval

X Tools for Claude MCP

by 0xGval

searchTwitter

Search Twitter content using natural language queries to find relevant tweets, filter by latest or top results, and control output with pagination and formatting options.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
sectionNolatest
limitNo

Implementation Reference

  • The registered tool handler that performs the search using helper functions and returns formatted results or error message.
      async ({ query, section, limit }) => {
        try {
          // Use the search function with the query directly
          const tweets = await performTwitterSearch(query, section, limit);
          
          // Format the response
          return {
            content: [{ 
              type: "text", 
              text: formatTwitterResults(query, tweets, section)
            }]
          };
        } catch (error) {
          console.error('Error searching Twitter:', error);
          return {
            content: [{ 
              type: "text", 
              text: `Error searching Twitter: ${error.message}`
            }]
          };
        }
      }
    );
  • Zod input schema for the searchTwitter tool defining query, section, and limit parameters.
      query: z.string().min(1, "Search query is required"),
      section: z.enum(["latest", "top"]).optional().default("latest"),
      limit: z.number().int().positive().optional().default(20)
    },
  • Registration of the searchTwitter tool using server.tool() with schema and handler.
      server.tool("searchTwitter",
        { 
          query: z.string().min(1, "Search query is required"),
          section: z.enum(["latest", "top"]).optional().default("latest"),
          limit: z.number().int().positive().optional().default(20)
        },
        async ({ query, section, limit }) => {
          try {
            // Use the search function with the query directly
            const tweets = await performTwitterSearch(query, section, limit);
            
            // Format the response
            return {
              content: [{ 
                type: "text", 
                text: formatTwitterResults(query, tweets, section)
              }]
            };
          } catch (error) {
            console.error('Error searching Twitter:', error);
            return {
              content: [{ 
                type: "text", 
                text: `Error searching Twitter: ${error.message}`
              }]
            };
          }
        }
      );
    }
  • Helper function performing paginated Twitter searches using RapidAPI.
    const performTwitterSearch = async (query, section, limit) => {
      // Check for API key
      if (!RAPIDAPI_KEY) {
        throw new Error("RAPIDAPI_KEY environment variable is not set");
      }
      
      // Log the query for debugging
      console.error(`TWITTER SEARCH: ${query}`);
      
      // Track all fetched tweets
      let allTweets = [];
      let continuationToken = null;
      
      // RapidAPI has a max of 20 per request, so we'll need to paginate
      const maxPerRequest = 20;
      const requestsNeeded = Math.ceil(limit / maxPerRequest);
      
      // Make requests until we hit the limit or run out of results
      for (let i = 0; i < requestsNeeded; i++) {
        // Build the query parameters
        const params = new URLSearchParams({
          query: query,
          section: section,
          limit: Math.min(maxPerRequest, limit - allTweets.length).toString()
        });
        
        // Add continuation token if available
        if (continuationToken) {
          params.append('continuation_token', continuationToken);
        }
        
        // Make the API request
        const response = await axios({
          method: 'GET',
          url: `https://twitter154.p.rapidapi.com/search/search?${params.toString()}`,
          headers: {
            'x-rapidapi-key': RAPIDAPI_KEY,
            'x-rapidapi-host': RAPIDAPI_HOST
          }
        });
        
        // Extract tweets and continuation token
        const newTweets = response.data.results || [];
        allTweets = [...allTweets, ...newTweets];
        
        // Store continuation token for next request
        continuationToken = response.data.continuation_token;
        
        // Stop if we don't have a continuation token or reached our limit
        if (!continuationToken || allTweets.length >= limit) {
          break;
        }
      }
      
      // Return only up to the requested limit
      return allTweets.slice(0, limit);
    };
  • Helper function to format Twitter search results into readable Markdown output.
    function formatTwitterResults(query, tweets, section) {
      if (!tweets || tweets.length === 0) {
        return `No tweets found for query: ${query}`;
      }
      
      let output = [];
      
    
      
      tweets.forEach((tweet, index) => {
        // Create clear separation between tweets
        output.push(`## [${index + 1}] Tweet by @${tweet.user.username}`);
        
        // User information
        let userInfo = `**User:** ${tweet.user.name} (@${tweet.user.username})`;
        if (tweet.user.is_blue_verified) {
          userInfo += ` [Verified]`;
        } else if (tweet.user.is_verified) {
          userInfo += ` [Verified]`;
        }
        output.push(userInfo);
        
        // User stats if available
        if (tweet.user) {
          const userStats = [];
          if (tweet.user.follower_count !== undefined) userStats.push(`${tweet.user.follower_count} followers`);
          if (tweet.user.following_count !== undefined) userStats.push(`${tweet.user.following_count} following`);
          if (userStats.length > 0) {
            output.push(`**Account stats:** ${userStats.join(', ')}`);
          }
        }
        
        // Tweet content
        output.push(`\n**Content:** ${tweet.text}\n`);
        
        // Engagement metrics
        let metrics = [];
        metrics.push(`${tweet.favorite_count} likes`);
        metrics.push(`${tweet.retweet_count} retweets`);
        metrics.push(`${tweet.reply_count} replies`);
        
        // Add quotes and bookmarks if available
        if (tweet.quote_count) metrics.push(`${tweet.quote_count} quotes`);
        if (tweet.bookmark_count) metrics.push(`${tweet.bookmark_count} bookmarks`);
        
        // Add view count if available
        if (tweet.views) metrics.push(`${tweet.views} views`);
        
        output.push(`**Engagement:** ${metrics.join(' | ')}`);
        
        // Creation date - fix the Invalid Date issue
        try {
          // Try parsing the date properly
          const date = new Date(tweet.created_at || tweet.creation_date);
          const formattedDate = !isNaN(date.getTime()) ? 
            `${date.toLocaleDateString('en-GB')} ${date.toLocaleTimeString('en-GB')}` : 
            'Date unavailable';
          output.push(`**Posted:** ${formattedDate}`);
        } catch (e) {
          output.push(`**Posted:** Date format error`);
        }
        
       
        
        // Add reply info if it's a reply
        if (tweet.in_reply_to_status_id_str) {
          output.push(`**Reply to:** https://twitter.com/status/${tweet.in_reply_to_status_id_str}`);
        }
        
        // Add media if available
        if (tweet.media && tweet.media.length > 0) {
          output.push(`**Media:** ${tweet.media.length} attachment(s)`);
          tweet.media.forEach(media => {
            output.push(`  - ${media.media_url_https || media.media_url}`);
          });
        }
        
        // Add video info if available
        if ((tweet.extended_entities && 
             tweet.extended_entities.media && 
             tweet.extended_entities.media.some(m => m.type === "video" || m.type === "animated_gif")) || 
            tweet.video_url) {
          output.push(`**Video:** ${tweet.video_url || "Multiple formats available"}`);
        }
        
        // Add tweet URL - construct a proper URL
        const tweetId = tweet.id_str || tweet.tweet_id;
        if (tweetId && tweet.user && tweet.user.username) {
          output.push(`**URL:** https://twitter.com/${tweet.user.username}/status/${tweetId}`);
        } else {
          output.push(`**URL:** Unable to construct URL (missing id or username)`);
        }
        
        
        
        // Add separator between tweets
        output.push('\n---\n');
      });
      
     
      
      return output.join('\n');
    } 
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/0xGval/twitter-X-mcp-server'

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