X (Twitter) MCP server

Instructions

Implementation Reference

• src/x_twitter_mcp/server.py:365-365 (registration)

  Registers the 'search_twitter' tool with FastMCP server using the @server.tool decorator, specifying the name and description.

  @server.tool(name="search_twitter", description="Search Twitter with a query")

• src/x_twitter_mcp/server.py:366-366 (schema)

  Defines the input schema via type hints: query (str), product (Optional[str]), count (Optional[int]), cursor (Optional[str]); output as List[Dict]. Includes docstring with parameter descriptions.

  async def search_twitter(query: str, product: Optional[str] = "Top", count: Optional[int] = 100, cursor: Optional[str] = None) -> List[Dict]:

• src/x_twitter_mcp/server.py:367-391 (handler)

  Executes the tool: determines sort_order from product, clamps count to 10-100, initializes Twitter client, performs search_recent_tweets, returns list of tweet dictionaries.

  """Searches Twitter for recent tweets.
  
  Args:
      query (str): The search query. Supports operators like #hashtag, from:user, etc.
      product (Optional[str]): Sorting preference. 'Top' for relevancy (default), 'Latest' for recency.
      count (Optional[int]): Number of tweets to retrieve. Default 100. Min 10, Max 100 for search_recent_tweets.
      cursor (Optional[str]): Pagination token (next_token) for fetching the next set of results.
  """
  sort_order = "relevancy" if product == "Top" else "recency"
  
  # Ensure count is within the allowed range (10-100)
  if count is None:
      effective_count = 100 # Default to 100 if not provided
  elif count < 10:
      logger.info(f"Requested count {count} is less than minimum 10. Using 10 instead.")
      effective_count = 10
  elif count > 100:
      logger.info(f"Requested count {count} is greater than maximum 100. Using 100 instead.")
      effective_count = 100
  else:
      effective_count = count
      
  client, _ = initialize_twitter_clients()
  tweets = client.search_recent_tweets(query=query, max_results=effective_count, sort_order=sort_order, next_token=cursor, tweet_fields=["id", "text", "created_at"])
  return [tweet.data for tweet in tweets.data]