nft-analytics-mcp

Instructions

Retrieve daily trading volume for top 5 Ethereum NFT collections.

Args:
    limit (int, optional): Maximum number of rows to fetch from the query. Defaults to 1000.

Returns:
    str: Markdown table of daily trading volumes by collection, or error message if the query fails.

Implementation Reference

• main.py:46-64 (handler)

  Handler function decorated with @mcp.tool(). Fetches data from Dune query ID 5140422 using the get_latest_result helper, processes it into a pivot table of daily trading volumes by collection using pandas, sorts by date descending, and returns a markdown table or error string.

  def get_daily_trading_volume_by_collection(limit: int = 1000) -> str:
      """
      Retrieve daily trading volume for top 5 Ethereum NFT collections.
  
      Args:
          limit (int, optional): Maximum number of rows to fetch from the query. Defaults to 1000.
  
      Returns:
          str: Markdown table of daily trading volumes by collection, or error message if the query fails.
      """
      try:
          data = get_latest_result(5140422, limit=limit)
          df = pd.DataFrame(data)
          df["day"] = pd.to_datetime(df["day"]).dt.date
          pivot_df = df.pivot(index="day", columns="collection", values="daily_volume")
          pivot_df = pivot_df.sort_index(ascending=False)
          return pivot_df.to_markdown()
      except Exception as e:
          return str(e)

• main.py:21-43 (helper)

  Helper function to fetch the latest execution results from a Dune Analytics query API using httpx, returning the rows as list of dicts.

  def get_latest_result(query_id: int, limit: int = 1000) -> list:
      """
      Fetch the latest results from a Dune Analytics query.
  
      Args:
          query_id (int): The ID of the Dune query to fetch results from.
          limit (int, optional): Maximum number of rows to return. Defaults to 1000.
  
      Returns:
          list: A list of dictionaries containing the query results, or an empty list if the request fails.
  
      Raises:
          httpx.HTTPStatusError: If the API request fails due to a client or server error.
      """
      url = f"{BASE_URL}/query/{query_id}/results"
      params = {"limit": limit}
      with httpx.Client() as client:
          response = client.get(url, params=params, headers=HEADERS, timeout=300)
          response.raise_for_status()
          data = response.json()
          
      result_data = data.get("result", {}).get("rows", [])
      return result_data

• main.py:46-46 (registration)

  The tool is registered using the @mcp.tool() decorator on the handler function.

  def get_daily_trading_volume_by_collection(limit: int = 1000) -> str: