GCP MCP

Instructions

    Upload a file to a Cloud Storage bucket.
    
    Args:
        project_id: The ID of the GCP project
        bucket_name: The name of the bucket to upload to
        source_file_path: The local file path to upload
        destination_blob_name: The name to give the file in GCS (default: filename from source)
        content_type: The content type of the file (default: auto-detect)
    
    Returns:
        Result of the upload operation
    

Implementation Reference

• src/gcp_mcp/gcp_modules/storage/tools.py:137-180 (handler)

  The core handler function for the 'upload_object' tool, which uploads a local file to a GCP Cloud Storage bucket using the Google Cloud Storage client.

      @mcp.tool()
      def upload_object(project_id: str, bucket_name: str, source_file_path: str, destination_blob_name: Optional[str] = None, content_type: Optional[str] = None) -> str:
          """
          Upload a file to a Cloud Storage bucket.
          
          Args:
              project_id: The ID of the GCP project
              bucket_name: The name of the bucket to upload to
              source_file_path: The local file path to upload
              destination_blob_name: The name to give the file in GCS (default: filename from source)
              content_type: The content type of the file (default: auto-detect)
          
          Returns:
              Result of the upload operation
          """
          try:
              import os
              from google.cloud import storage
              
              # Initialize the Storage client
              client = storage.Client(project=project_id)
              
              # Get the bucket
              bucket = client.get_bucket(bucket_name)
              
              # If no destination name is provided, use the source filename
              if not destination_blob_name:
                  destination_blob_name = os.path.basename(source_file_path)
              
              # Create a blob object
              blob = bucket.blob(destination_blob_name)
              
              # Upload the file
              blob.upload_from_filename(source_file_path, content_type=content_type)
              
              return f"""
  File successfully uploaded:
  - Source: {source_file_path}
  - Destination: gs://{bucket_name}/{destination_blob_name}
  - Size: {blob.size / (1024 * 1024):.2f} MB
  - Content-Type: {blob.content_type}
  """
          except Exception as e:
              return f"Error uploading file: {str(e)}"

• src/gcp_mcp/server.py:41-42 (registration)

  Registers all storage tools, including 'upload_object', by invoking the module's register_tools function on the MCP server instance.

  # Register storage tools
  storage_tools.register_tools(mcp)

• src/gcp_mcp/server.py:9-9 (registration)

  Imports the storage tools module containing the 'upload_object' tool implementation and registration logic.

  from .gcp_modules.storage import tools as storage_tools

• src/gcp_mcp/gcp_modules/storage/tools.py:138-151 (schema)

  The function signature and docstring defining the input schema (parameters) and output description for the 'upload_object' tool.

  def upload_object(project_id: str, bucket_name: str, source_file_path: str, destination_blob_name: Optional[str] = None, content_type: Optional[str] = None) -> str:
      """
      Upload a file to a Cloud Storage bucket.
      
      Args:
          project_id: The ID of the GCP project
          bucket_name: The name of the bucket to upload to
          source_file_path: The local file path to upload
          destination_blob_name: The name to give the file in GCS (default: filename from source)
          content_type: The content type of the file (default: auto-detect)
      
      Returns:
          Result of the upload operation
      """