MCP Server Demo

Instructions

Implementation Reference

• server.py:22-95 (handler)

  The @mcp.tool() decorated function implementing fetch_news_articles. It fetches news articles from WorldNewsAPI based on query_text, date ranges, and max_results, paginating results and formatting them into a dictionary list.
  @mcp.tool() def fetch_news_articles( query_text="politics", earliest_date="2025-04-17", latest_date="2025-04-23", max_results=5, ) -> dict: """ Fetches news articles from the WorldNewsAPI based on specified parameters and returns them as a list of dictionaries. Args: query_text (str): The text to search for in news articles earliest_date (str): Earliest publication date in YYYY-MM-DD format latest_date (str): Latest publication date in YYYY-MM-DD format max_results (int): Maximum number of results to return Returns: list: A list of dictionaries containing article details """ try: newsapi_instance = worldnewsapi.NewsApi( worldnewsapi.ApiClient(newsapi_configuration) ) offset = 0 all_results = [] max_results = int(max_results) # Ensure max_results is an integer while len(all_results) < max_results: request_count = min( 100, max_results - len(all_results) ) # request 100 or the remaining number of articles response = newsapi_instance.search_news( text=query_text, earliest_publish_date=earliest_date, latest_publish_date=latest_date, sort="publish-time", sort_direction="desc", # min_sentiment=-0.8, # Ensuring this is a float # max_sentiment=0.8, # Ensuring this is a float offset=offset, number=request_count, ) # print(f"Retrieved {len(response.news)} articles. Offset: {offset}/{max_results}. " # f"Total available: {response.available}.") if len(response.news) == 0: break all_results.extend(response.news) offset += 100 # Convert API response objects to dictionaries articles_list = [] for article in all_results[:max_results]: # Use max_results here article_dict = { "title": article.title, "author": article.authors, "url": article.url, "text_preview": article.text[:80] + "..." if article.text else "", "full_text": article.text, "publish_date": article.publish_date, } articles_list.append(article_dict) return {"all_data": articles_list} except worldnewsapi.ApiException as e: # print(f"Exception when calling NewsApi->search_news: {e}") return {"error": str(e)}