MCP Image Extractor

Instructions

Implementation Reference

• src/image-utils.ts:111-227 (handler)

  Core implementation of the extractImageFromFile handler: reads file, checks size, resizes to max 512x512, determines MIME type, compresses, encodes to base64, returns MCP response with metadata and image.
  export async function extractImageFromFile(params: ExtractImageFromFileParams): Promise<McpToolResponse> { try { const { file_path, resize, max_width, max_height } = params; // Check if file exists if (!fs.existsSync(file_path)) { return { content: [{ type: "text", text: `Error: File ${file_path} does not exist` }], isError: true }; } // Read file let imageBuffer = fs.readFileSync(file_path); // Check size if (imageBuffer.length > MAX_IMAGE_SIZE) { return { content: [{ type: "text", text: `Error: Image size exceeds maximum allowed size of ${MAX_IMAGE_SIZE} bytes` }], isError: true }; } // Process the image let metadata = await sharp(imageBuffer).metadata(); // Always resize to ensure the base64 representation is reasonable // This will help avoid consuming too much of the context window if (metadata.width && metadata.height) { // Use provided dimensions or fallback to defaults for optimal LLM context usage const targetWidth = Math.min(metadata.width, DEFAULT_MAX_WIDTH); const targetHeight = Math.min(metadata.height, DEFAULT_MAX_HEIGHT); // Only resize if needed if (metadata.width > targetWidth || metadata.height > targetHeight) { imageBuffer = await sharp(imageBuffer) .resize({ width: targetWidth, height: targetHeight, fit: 'inside', withoutEnlargement: true }) .toBuffer(); // Update metadata after resize metadata = await sharp(imageBuffer).metadata(); } } // Determine mime type based on file extension const fileExt = path.extname(file_path).toLowerCase(); let mimeType = 'image/jpeg'; let format = 'jpeg'; if (fileExt === '.png') { mimeType = 'image/png'; format = 'png'; } else if (fileExt === '.jpg' || fileExt === '.jpeg') { mimeType = 'image/jpeg'; format = 'jpeg'; } else if (fileExt === '.gif') { mimeType = 'image/gif'; format = 'gif'; } else if (fileExt === '.webp') { mimeType = 'image/webp'; format = 'webp'; } else if (fileExt === '.svg') { mimeType = 'image/svg+xml'; format = 'svg'; } else if (fileExt === '.avif') { mimeType = 'image/avif'; format = 'avif'; } // Compress the image based on its format try { imageBuffer = await compressImage(imageBuffer, format); } catch (compressionError) { console.warn('Compression warning, using original image:', compressionError); // Continue with the original image if compression fails } // Convert to base64 const base64 = imageBuffer.toString('base64'); // Return both text and image content return { content: [ { type: "text", text: JSON.stringify({ width: metadata.width, height: metadata.height, format: metadata.format, size: imageBuffer.length }) }, { type: "image", data: base64, mimeType: mimeType } ] }; } catch (error: unknown) { console.error('Error processing image file:', error); return { content: [{ type: "text", text: `Error: ${error instanceof Error ? error.message : String(error)}` }], isError: true }; } }
• src/image-utils.ts:29-34 (schema)

  TypeScript type definition for the input parameters of extractImageFromFile.
  export type ExtractImageFromFileParams = { file_path: string; resize: boolean; max_width: number; max_height: number; };
• src/index.ts:22-35 (registration)

  MCP tool registration for 'extract_image_from_file': defines name, description, Zod input schema, and thin async handler that calls the core extractImageFromFile function.
  server.tool( "extract_image_from_file", "Extract and analyze images from local file paths. Supports visual content understanding, OCR text extraction, and object recognition for screenshots, photos, diagrams, and documents.", { file_path: z.string().describe("Path to the image file to analyze (supports screenshots, photos, diagrams, and documents in PNG, JPG, GIF, WebP formats)"), resize: z.boolean().default(true).describe("For backward compatibility only. Images are always automatically resized to optimal dimensions (max 512x512) for LLM analysis"), max_width: z.number().default(512).describe("For backward compatibility only. Default maximum width is now 512px"), max_height: z.number().default(512).describe("For backward compatibility only. Default maximum height is now 512px") }, async (args, extra) => { const result = await extractImageFromFile(args); return result; } );
• src/image-utils.ts:78-108 (helper)

  Supporting helper function for compressing images using sharp based on detected format.
  async function compressImage(imageBuffer: Buffer, formatStr: string): Promise<Buffer> { const sharpInstance = sharp(imageBuffer); const format = formatStr.toLowerCase() as SupportedFormat; // Check if format is supported if (format in COMPRESSION_OPTIONS) { const options = COMPRESSION_OPTIONS[format]; // Use specific methods based on format switch (format) { case 'jpeg': case 'jpg': return await sharpInstance.jpeg(options as any).toBuffer(); case 'png': return await sharpInstance.png(options as any).toBuffer(); case 'webp': return await sharpInstance.webp(options as any).toBuffer(); case 'avif': return await sharpInstance.avif(options as any).toBuffer(); case 'tiff': return await sharpInstance.tiff(options as any).toBuffer(); // For formats without specific compression options case 'gif': case 'svg': return await sharpInstance.toBuffer(); } } // Default to jpeg if format not supported return await sharpInstance.jpeg(COMPRESSION_OPTIONS.jpeg as any).toBuffer(); }