describe_image_from_file
Generate detailed descriptions of local images by providing their absolute file path. Ideal for local file access, with guidance through optional prompts. Use with volume mapping in Docker environments.
Instructions
Describe an image from a local file path. Requires proper file system access.
Best for: Local files when the server has filesystem access to the path.
Limitations: When using Docker, requires volume mapping (-v flag) to access host files.
Not recommended for: Images uploaded to chat or images with public URLs.
Args:
filepath: Absolute path to the image file
prompt: Optional prompt to guide the description
Returns:
str: Detailed description of the image
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| filepath | Yes | ||
| prompt | No | Please describe this image in detail. |
Implementation Reference
- Main handler function for 'describe_image_from_file' tool. Registers the tool via @mcp.tool(), loads image from filepath, converts to base64, and delegates to internal describe_image processing logic.@mcp.tool() async def describe_image_from_file( filepath: str, prompt: str = "Please describe this image in detail." ) -> str: """Describe the contents of an image file using vision AI. Args: filepath: Path to the image file prompt: Optional prompt to use for the description. Returns: str: Detailed description of the image """ try: logger.info(f"Processing image file: {filepath}") # Convert image to base64 image_data, mime_type = image_to_base64(filepath) logger.info(f"Successfully converted image to base64. MIME type: {mime_type}") logger.debug(f"Base64 data length: {len(image_data)}") # Use describe_image tool result = await describe_image(image=image_data, prompt=prompt) if not result: raise ValueError("Received empty response from processing") return sanitize_output(result) except FileNotFoundError: logger.error(f"Image file not found: {filepath}") raise except ValueError as e: logger.error(f"Input error: {str(e)}") raise except Exception as e: logger.error(f"Error processing image file: {str(e)}", exc_info=True) raise
- Supporting utility to convert an image file to base64-encoded string and MIME type, directly called by the describe_image_from_file handler.def image_to_base64(image_path: str) -> Tuple[str, str]: """Convert an image file to base64 string and detect its MIME type. Args: image_path: Path to the image file Returns: Tuple of (base64_string, mime_type) Raises: FileNotFoundError: If image file doesn't exist ValueError: If file is not a valid image """ path = Path(image_path) if not path.exists(): logger.error(f"Image file not found: {image_path}") raise FileNotFoundError(f"Image file not found: {image_path}") try: # Try to open and validate the image with Image.open(path) as img: # Get image format and convert to MIME type format_to_mime = { "JPEG": "image/jpeg", "PNG": "image/png", "GIF": "image/gif", "WEBP": "image/webp", } mime_type = format_to_mime.get(img.format, "application/octet-stream") logger.info( f"Processing image: {image_path}, format: {img.format}, size: {img.size}" ) # Convert to base64 with path.open("rb") as f: base64_data = base64.b64encode(f.read()).decode("utf-8") logger.debug(f"Base64 data length: {len(base64_data)}") return base64_data, mime_type except UnidentifiedImageError as e: logger.error(f"Invalid image format: {str(e)}") raise ValueError(f"Invalid image format: {str(e)}") except OSError as e: logger.error(f"Failed to read image file: {str(e)}") raise ValueError(f"Failed to read image file: {str(e)}") except Exception as e: logger.error(f"Unexpected error processing image: {str(e)}", exc_info=True) raise ValueError(f"Failed to process image: {str(e)}")