get_info

Instructions

Implementation Reference

• src/dataset_viewer/server.py:472-492 (handler)

  The handler logic within the MCP tool dispatcher (@server.call_tool) that executes the get_info tool. It queries the Hugging Face datasets-server API /info endpoint directly and returns the dataset information as formatted JSON text content, handling 404 errors gracefully.

  if name == "get_info":
      dataset = arguments["dataset"]
      try:
          response = await DatasetViewerAPI(auth_token=auth_token).client.get("/info", params={"dataset": dataset})
          response.raise_for_status()
          result = response.json()
          return [
              types.TextContent(
                  type="text",
                  text=json.dumps(result, indent=2)
              )
          ]
      except httpx.HTTPStatusError as e:
          if e.response.status_code == 404:
              return [
                  types.TextContent(
                      type="text",
                      text=f"Dataset '{dataset}' not found"
                  )
              ]
          raise

• src/dataset_viewer/server.py:221-241 (registration)

  Registration of the 'get_info' MCP tool in the @server.list_tools() handler, defining the tool name, description, and input schema for dataset parameter.

  types.Tool(
      name="get_info",
      description="Get detailed information about a Hugging Face dataset including description, features, splits, and statistics. Run validate first to check if the dataset exists and is accessible.",
      inputSchema={
          "type": "object",
          "properties": {
              "dataset": {
                  "type": "string",
                  "description": "Hugging Face dataset identifier in the format owner/dataset",
                  "pattern": "^[^/]+/[^/]+$",
                  "examples": ["ylecun/mnist", "stanfordnlp/imdb"]
              },
              "auth_token": {
                  "type": "string",
                  "description": "Hugging Face auth token for private/gated datasets",
                  "optional": True
              }
          },
          "required": ["dataset"],
      }
  ),

• src/dataset_viewer/server.py:224-240 (schema)

  Input schema definition for the get_info tool, specifying the required 'dataset' parameter and optional auth_token.

  inputSchema={
      "type": "object",
      "properties": {
          "dataset": {
              "type": "string",
              "description": "Hugging Face dataset identifier in the format owner/dataset",
              "pattern": "^[^/]+/[^/]+$",
              "examples": ["ylecun/mnist", "stanfordnlp/imdb"]
          },
          "auth_token": {
              "type": "string",
              "description": "Hugging Face auth token for private/gated datasets",
              "optional": True
          }
      },
      "required": ["dataset"],
  }

• src/dataset_viewer/server.py:57-68 (helper)

  Helper method in DatasetViewerAPI class that performs the core API call for dataset info (similar to tool handler logic), used for caching dataset state.

  async def get_info(self, dataset: str) -> dict:
      """Get detailed information about a dataset"""
      try:
          # Get detailed dataset info
          response = await self.client.get("/info", params={"dataset": dataset})
          response.raise_for_status()
          return response.json()
      except httpx.HTTPStatusError as e:
          if e.response.status_code == 404:
              raise ValueError(f"Dataset '{dataset}' not found")
          raise