WebSearch

Instructions

Returns:
- Extracted information from the web page based on the prompt

Implementation Reference

• main.py:57-77 (handler)

  The primary handler function for the 'extract' MCP tool, registered with @mcp.tool(). It receives input parameters, calls the WebTools.extract_info helper, and handles errors.

  @mcp.tool()
  async def extract(
      url: list[str], prompt: str, enabaleWebSearch: bool, showSources: bool
  ) -> str:
      """Extracts specific information from a web page based on a prompt.
      Args:
      - url: The complete URL of the web page to extract information from
      - prompt: Instructions specifying what information to extract from the page
      - enabaleWebSearch: Whether to allow web searches to supplement the extraction
      - showSources: Whether to include source references in the response
  
      Returns:
      - Extracted information from the web page based on the prompt
      """
      try:
          info_extracted = webtools.extract_info(
              url, enabaleWebSearch, prompt, showSources
          )
          return info_extracted
      except Exception as e:
          return f"Error extracting information: {str(e)}"

• main.py:58-70 (schema)

  Input schema defined by function parameters and docstring describing args and return type for the 'extract' tool.

  async def extract(
      url: list[str], prompt: str, enabaleWebSearch: bool, showSources: bool
  ) -> str:
      """Extracts specific information from a web page based on a prompt.
      Args:
      - url: The complete URL of the web page to extract information from
      - prompt: Instructions specifying what information to extract from the page
      - enabaleWebSearch: Whether to allow web searches to supplement the extraction
      - showSources: Whether to include source references in the response
  
      Returns:
      - Extracted information from the web page based on the prompt
      """

• tools/webtools.py:38-56 (helper)

  Supporting helper method in WebTools class that implements the core extraction logic by calling FirecrawlApp.extract with configured options.

  def extract_info(
      self, url: list[str], enableWebSearch: bool, prompt: str, showSources: bool
  ):
      try:
          info_extracted = self.firecrawl.extract(
              url,
              {
                  "prompt": prompt,
                  "enableWebSearch": enableWebSearch,
                  "showSources": showSources,
                  "scrapeOptions": {
                      "formats": ["markdown"],
                      "blockAds": True,
                  },
              },
          )
          return info_extracted
      except Exception as e:
          return f"Error extracting information from page {url}: {str(e)}"

• main.py:57-57 (registration)

  The @mcp.tool() decorator registers the 'extract' function as an MCP tool.

  @mcp.tool()