google_search_images

Instructions

Implementation Reference

• src/serper_mcp_server/core.py:14-17 (handler)

  The 'google' handler function that executes the tool logic for google_search_images. It takes a SerperTools enum value (GOOGLE_SEARCH_IMAGES) and a request model, extracts the URI path by taking the last part of the tool name (e.g., 'images'), and makes a POST request to https://google.serper.dev/images with the Serper API.

  async def google(tool: SerperTools, request: BaseModel) -> Dict[str, Any]:
      uri_path = tool.value.split("_")[-1]
      url = f"https://google.serper.dev/{uri_path}"
      return await fetch_json(url, request)

• src/serper_mcp_server/schemas.py:25-33 (schema)

  SearchRequest schema is used for google_search_images input validation. Contains fields: q (query), gl (country), location, hl (language), page, tbs (time period), and num (number of results).

  class SearchRequest(BaseRequest):
      tbs: Optional[str] = Field(
          None, description="The time period to search in, e.g. d, w, m, y"
      )
      num: str = Field(
          "10",
          pattern=r"^([1-9]|[1-9]\d|100)$",
          description="The number of results to return, max is 100 (integer value as string)",
      )

• src/serper_mcp_server/server.py:62-78 (registration)

  The 'call_tool' function dispatches incoming tool requests. When name matches 'google_search_images', it creates a SearchRequest from arguments and calls google() with the SerperTools.GOOGLE_SEARCH_IMAGES enum.

  @server.call_tool()
  async def call_tool(name: str, arguments: dict[str, Any]) -> Sequence[TextContent | ImageContent | EmbeddedResource]:
      if not SERPER_API_KEY:
          return [TextContent(text=f"SERPER_API_KEY is empty!", type="text")]
  
      try:
          if name == SerperTools.WEBPAGE_SCRAPE.value:
              request = WebpageRequest(**arguments)
              result = await scape(request)
              return [TextContent(text=json.dumps(result, indent=2), type="text")]
  
          if not SerperTools.has_value(name):
              raise ValueError(f"Tool {name} not found")
  
          tool = SerperTools(name)
          request = google_request_map[tool](**arguments)
          result = await google(tool, request)

• src/serper_mcp_server/server.py:41-60 (registration)

  The 'list_tools' function registers google_search_images as a Tool with name from the enum and description 'Search Google for results', using SearchRequest schema.

  @server.list_tools()
  async def list_tools() -> List[Tool]:
      tools = []
  
      for k, v in google_request_map.items():
          tools.append(
              Tool(
                  name=k.value,
                  description="Search Google for results",
                  inputSchema=v.model_json_schema(),
              ),
          )
  
      tools.append(Tool(
          name=SerperTools.WEBPAGE_SCRAPE,
          description="Scrape webpage by url",
          inputSchema=WebpageRequest.model_json_schema(),
      ))
  
      return tools

• src/serper_mcp_server/core.py:25-39 (helper)

  The 'fetch_json' helper makes the actual HTTP POST request to the Serper API with the appropriate headers and payload, used by the google() handler.

  async def fetch_json(url: str, request: BaseModel) -> Dict[str, Any]:
      payload = request.model_dump(exclude_none=True)
      headers = {
          'X-API-KEY': SERPER_API_KEY,
          'Content-Type': 'application/json'
      }
  
      ssl_context = ssl.create_default_context(cafile=certifi.where())
      connector = aiohttp.TCPConnector(ssl=ssl_context)
  
      timeout = aiohttp.ClientTimeout(total=AIOHTTP_TIMEOUT)
      async with aiohttp.ClientSession(connector=connector, timeout=timeout) as session:
          async with session.post(url, headers=headers, json=payload) as response:
              response.raise_for_status()
              return await response.json()