Emotion Dataset Analysis MCP Server

Instructions

Implementation Reference

• server.py:110-140 (handler)

  The `search_text` tool implementation, annotated with `@mcp.tool()`, which searches the dataset for a given string.

  @mcp.tool()
  def search_text(query: str, limit: int = 10) -> str:
      """Search for samples containing specific text.
  
      Args:
          query: Text to search for (case-insensitive)
          limit: Maximum results to return (default: 10)
  
      Returns:
          JSON string with matching samples
      """
      query = query.lower()
      limit = min(max(limit, 1), 50)
      dataset = get_dataset()
  
      matches = []
      for idx, sample in enumerate(dataset):
          if query in sample["text"].lower():
              matches.append({
                  "text": sample["text"],
                  "emotion": EMOTION_LABELS[sample["label"]],
                  "index": idx
              })
              if len(matches) >= limit:
                  break
  
      return json.dumps({
          "query": query,
          "found": len(matches),
          "matches": matches
      }, indent=2)