{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-imagesorcery-mcp","slug":"imagesorcery-mcp","name":"ImageSorcery MCP","type":"mcp","url":"https://github.com/sunriseapps/imagesorcery-mcp","page_url":"https://unfragile.ai/imagesorcery-mcp","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-imagesorcery-mcp__cap_0","uri":"capability://image.visual.yolo.based.object.detection.with.bounding.box.extraction","name":"yolo-based object detection with bounding box extraction","description":"Detects objects in images using YOLO (You Only Look Once) models running locally via the FastMCP server, returning structured bounding box coordinates, class labels, and confidence scores without sending image data to external APIs. The system manages model lifecycle through a post-installation script that automatically downloads YOLO weights and caches them in the models/ directory, enabling offline operation after initial setup.","intents":["I need to identify and locate specific objects in an image programmatically","I want to extract bounding box coordinates for downstream image manipulation tasks","I need object detection that keeps image data private and runs locally"],"best_for":["AI assistants (Claude, Cursor, Cline) performing vision-based automation","developers building privacy-sensitive image processing workflows","teams requiring offline computer vision without cloud API dependencies"],"limitations":["YOLO detection accuracy varies by model size (nano/small/medium/large) — larger models are slower but more accurate","Requires GPU or significant CPU resources for real-time performance on high-resolution images","Model weights are large (50-200MB depending on variant) and must be downloaded during post-installation setup","Detection performance degrades on images with extreme lighting, occlusion, or out-of-distribution objects"],"requires":["Python 3.9+","FastMCP framework installed","YOLO model weights pre-downloaded via post_install.py script","OpenCV library for image I/O and preprocessing","Sufficient disk space for model weights (minimum 500MB)"],"input_types":["image file path (local filesystem)","image URL (downloaded and cached locally)","base64-encoded image data"],"output_types":["structured JSON with array of detections containing: class_name, confidence_score, bounding_box (x, y, width, height)"],"categories":["image-visual","computer-vision"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_1","uri":"capability://image.visual.clip.based.semantic.image.search.and.classification","name":"clip-based semantic image search and classification","description":"Performs zero-shot image classification and semantic search using CLIP (Contrastive Language-Image Pre-training) models that encode both images and text into a shared embedding space, enabling AI assistants to classify images against arbitrary text labels without retraining. The system uses cosine similarity between image and text embeddings to rank matches, with model weights automatically downloaded via download_clip.py during setup.","intents":["I need to classify an image against custom text labels without training a model","I want to find images semantically similar to a text description","I need to determine if an image matches a specific concept or category"],"best_for":["AI assistants performing flexible image categorization with dynamic labels","developers building semantic search without labeled training data","teams needing zero-shot classification for rapidly changing categories"],"limitations":["CLIP performance depends on label specificity — vague descriptions produce lower-quality results","Embedding computation is slower than traditional classifiers (typically 100-500ms per image on CPU)","Model weights are large (1-5GB depending on variant) and require significant memory during inference","Cross-lingual and domain-specific performance may be limited depending on training data coverage"],"requires":["Python 3.9+","CLIP model weights pre-downloaded via download_clip.py script","PyTorch or ONNX runtime for embedding computation","Minimum 4GB RAM for model loading, 8GB+ recommended","FastMCP framework integration"],"input_types":["image file path","image URL","base64-encoded image","text labels or descriptions (array of strings)"],"output_types":["structured JSON with similarity scores for each label, ranked by confidence"],"categories":["image-visual","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_10","uri":"capability://image.visual.multi.layer.image.composition.and.overlay.blending","name":"multi-layer image composition and overlay blending","description":"Composites multiple images together using alpha blending and layer operations through OpenCV's addWeighted and bitwise operations, enabling AI assistants to combine images, apply watermarks, or create composite visualizations. The capability supports configurable opacity, blending modes, and positioning of overlay images.","intents":["I need to overlay one image on top of another with transparency","I want to add a watermark or logo to an image","I need to composite multiple images into a single output"],"best_for":["AI assistants creating composite images and visualizations","developers building image annotation pipelines","teams automating watermarking or branding workflows"],"limitations":["Overlay positioning requires manual specification — no automatic alignment or content-aware placement","Blending quality depends on image formats and alpha channel support — JPEG overlays may have artifacts","Performance scales with image size and number of layers — complex composites can be slow"],"requires":["Python 3.9+","OpenCV library with alpha blending support","Valid image file paths or URLs for base and overlay images","Overlay parameters: position (x, y), opacity (0-1), blending mode"],"input_types":["base image file path or URL","overlay image file path or URL","overlay parameters: x, y, opacity, blending_mode"],"output_types":["composite image file (PNG with alpha, or JPEG)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_11","uri":"capability://image.visual.annotation.drawing.with.text.labels.and.geometric.shapes","name":"annotation drawing with text labels and geometric shapes","description":"Draws text, rectangles, circles, lines, and arrows on images using OpenCV's drawing functions (putText, rectangle, circle, line, arrowedLine), enabling AI assistants to annotate detection results, create visualizations, or mark regions of interest. The capability supports configurable colors, line widths, and font properties for flexible annotation styling.","intents":["I need to draw bounding boxes around detected objects","I want to add text labels or annotations to an image","I need to visualize detection results or analysis output"],"best_for":["AI assistants visualizing detection and analysis results","developers building image annotation pipelines","teams creating annotated datasets or visual reports"],"limitations":["Text rendering quality depends on font availability and size — small fonts may be unreadable","Drawing operations modify the original image — no non-destructive annotation","Coordinate specification is manual — no automatic layout or collision detection for overlapping annotations"],"requires":["Python 3.9+","OpenCV library with drawing functions","Valid image file path or URL","Drawing parameters: coordinates, colors (BGR), line width, font properties"],"input_types":["image file path or URL","drawing specifications: shape_type (text/rectangle/circle/line/arrow), coordinates, color, line_width, font_properties"],"output_types":["annotated image file (PNG, JPEG, or original format)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_12","uri":"capability://tool.use.integration.mcp.protocol.based.tool.invocation.and.parameter.validation","name":"mcp protocol-based tool invocation and parameter validation","description":"Exposes image processing operations as MCP tools with standardized schema-based parameter validation, enabling AI clients (Claude, Cursor, Cline) to discover, invoke, and chain image processing operations through the Model Control Protocol. The FastMCP framework handles tool registration, parameter marshaling, and error handling through a middleware stack that validates inputs against JSON schemas.","intents":["I need to call image processing tools from an AI assistant with parameter validation","I want to discover available image processing capabilities through MCP","I need to chain multiple image operations in a workflow"],"best_for":["AI assistants (Claude, Cursor, Cline) performing image processing","developers building MCP-based image processing integrations","teams standardizing on MCP for tool orchestration"],"limitations":["Parameter validation adds overhead — complex schemas can slow tool invocation","Tool discovery requires MCP client support — not all AI assistants fully support MCP","Error handling is limited to MCP protocol constraints — detailed error messages may be truncated"],"requires":["FastMCP framework installed and configured","MCP-compatible AI client (Claude, Cursor, Cline)","MCP server running and accessible via stdio or HTTP transport","Tool schemas defined in JSON Schema format"],"input_types":["MCP tool invocation with parameters matching JSON schema"],"output_types":["MCP tool result with structured output (JSON or file reference)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_13","uri":"capability://automation.workflow.model.lifecycle.management.and.automatic.provisioning","name":"model lifecycle management and automatic provisioning","description":"Automatically downloads, caches, and manages computer vision model weights (YOLO, CLIP, EasyOCR) through post-installation scripts (post_install.py, download_models.py, download_clip.py) that provision models into a models/ directory, enabling zero-configuration operation after setup. The system tracks model metadata and provides resource listings through the models://list resource.","intents":["I need to set up image processing models without manual configuration","I want to verify available models and their metadata","I need to manage model versions and updates"],"best_for":["developers deploying ImageSorcery MCP in new environments","teams automating model provisioning in CI/CD pipelines","users wanting zero-configuration setup after installation"],"limitations":["Initial setup requires downloading large model files (1-5GB total) — slow on limited bandwidth","Model updates require re-running provisioning scripts — no automatic update mechanism","Disk space requirements are significant (minimum 500MB-2GB) — may be problematic on resource-constrained systems","Model versions are pinned at setup time — no easy way to switch between model variants"],"requires":["Python 3.9+","Internet connectivity for initial model downloads","Sufficient disk space (minimum 2GB)","post_install.py script execution permissions","pip package manager"],"input_types":["none (automatic provisioning during setup)"],"output_types":["downloaded model files in models/ directory, model metadata in JSON format"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_14","uri":"capability://planning.reasoning.complex.workflow.orchestration.through.mcp.prompts","name":"complex workflow orchestration through mcp prompts","description":"Defines multi-step image processing workflows (e.g., remove-background) as MCP prompts that orchestrate multiple tools in sequence, enabling AI assistants to execute complex operations through natural language instructions that are expanded into tool invocation chains. The system uses prompt templates to guide AI reasoning and tool selection.","intents":["I need to remove image backgrounds using a coordinated sequence of detection and masking operations","I want to execute complex image processing workflows through natural language","I need to guide AI assistants through multi-step image processing tasks"],"best_for":["AI assistants performing complex image processing workflows","developers building high-level image processing abstractions","teams standardizing on workflow patterns for common tasks"],"limitations":["Prompt-based orchestration depends on AI model reasoning — results may be inconsistent or suboptimal","Workflow execution is sequential — no parallel execution of independent steps","Error handling in multi-step workflows is limited — failure in one step may cascade","Prompt templates require manual maintenance and tuning for different image types"],"requires":["FastMCP framework with prompt support","MCP-compatible AI client with prompt execution capability","Underlying tools (detect, find, ocr, etc.) properly configured","Prompt templates defined in MCP format"],"input_types":["natural language instruction matching prompt template","image file path or URL"],"output_types":["processed image file with workflow results"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_15","uri":"capability://automation.workflow.configuration.management.and.runtime.parameter.control","name":"configuration management and runtime parameter control","description":"Provides a configuration system (config.py) that manages runtime parameters for image processing operations, model selection, and server behavior through environment variables and configuration files. The system exposes a config tool through MCP that allows AI assistants to query and modify settings at runtime without restarting the server.","intents":["I need to adjust image processing parameters like blur kernel size or detection confidence","I want to query current configuration and available options","I need to switch between model variants (YOLO nano vs large) at runtime"],"best_for":["developers tuning image processing parameters for specific use cases","teams managing multi-environment deployments with different configurations","AI assistants adapting processing parameters based on image characteristics"],"limitations":["Configuration changes at runtime may not apply to already-loaded models","No validation of configuration values — invalid settings may cause runtime errors","Configuration persistence requires manual file management — no built-in state storage"],"requires":["Python 3.9+","FastMCP framework","Configuration file or environment variables","MCP client support for config tool"],"input_types":["configuration key-value pairs (strings, numbers, booleans)"],"output_types":["current configuration state in JSON format"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_2","uri":"capability://image.visual.easyocr.based.text.extraction.from.images","name":"easyocr-based text extraction from images","description":"Extracts text from images using EasyOCR, a multi-language optical character recognition library that runs locally within the MCP server, returning recognized text with bounding boxes and confidence scores. The system supports 80+ languages and handles rotated/skewed text through preprocessing, with model weights cached after initial download.","intents":["I need to extract text content from screenshots, scanned documents, or photos","I want to identify and locate text regions within an image for further processing","I need OCR that works offline and preserves text positioning information"],"best_for":["AI assistants processing screenshots and document images","developers building document automation workflows","teams requiring multi-language OCR without cloud service dependencies"],"limitations":["OCR accuracy varies significantly with image quality, resolution, and font type — low-quality images may have 20-40% error rates","Processing time scales with image size and text density (typically 500ms-5s per image)","Model weights are large and require significant disk space (1-2GB for multi-language support)","Performance degrades on handwritten text, unusual fonts, and non-standard layouts"],"requires":["Python 3.9+","EasyOCR library installed","Model weights pre-downloaded during setup","Minimum 2GB disk space for language models","PyTorch or ONNX runtime"],"input_types":["image file path","image URL","base64-encoded image"],"output_types":["structured JSON with extracted text, bounding boxes (x, y, width, height), and per-character confidence scores"],"categories":["image-visual","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_3","uri":"capability://image.visual.image.metadata.extraction.and.analysis","name":"image metadata extraction and analysis","description":"Extracts comprehensive metadata from images including dimensions, color space, EXIF data, file size, and format information through OpenCV and PIL/Pillow libraries integrated into the MCP server. This capability provides structured analysis of image properties without modification, enabling AI assistants to understand image characteristics before applying transformations.","intents":["I need to check image dimensions and format before processing","I want to extract EXIF metadata like camera settings and GPS coordinates","I need to analyze color space and bit depth for compatibility checking"],"best_for":["AI assistants validating image properties before batch processing","developers building image pipeline tools with format detection","teams analyzing image collections for metadata-driven workflows"],"limitations":["EXIF data availability depends on image source — smartphone photos typically have rich metadata, screenshots often have minimal data","Some image formats (WebP, AVIF) may have limited metadata support depending on library versions","GPS coordinates in EXIF data may be outdated or intentionally stripped for privacy"],"requires":["Python 3.9+","OpenCV and PIL/Pillow libraries","FastMCP framework"],"input_types":["image file path","image URL"],"output_types":["structured JSON with: width, height, format, color_space, file_size_bytes, exif_data (if available), bit_depth"],"categories":["image-visual","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_4","uri":"capability://image.visual.precision.image.cropping.with.coordinate.based.region.extraction","name":"precision image cropping with coordinate-based region extraction","description":"Crops images to specified rectangular regions using pixel-level coordinate inputs (x, y, width, height) through OpenCV's array slicing, enabling AI assistants to extract specific areas of interest identified by detection or analysis tools. The capability preserves image quality and supports both absolute coordinates and relative positioning.","intents":["I need to extract a specific region from an image identified by object detection","I want to remove margins or crop to a region of interest","I need to prepare image patches for downstream processing or analysis"],"best_for":["AI assistants chaining detection and cropping operations","developers building image preprocessing pipelines","teams automating image region extraction workflows"],"limitations":["Cropping outside image bounds will fail — requires validation of coordinates against image dimensions","No automatic content-aware cropping — coordinates must be explicitly specified","Quality loss occurs if cropping to very small regions (< 10x10 pixels) due to compression artifacts"],"requires":["Python 3.9+","OpenCV library","Valid image file path or URL","Coordinates within image bounds"],"input_types":["image file path","image URL","base64-encoded image","crop parameters: x, y, width, height (integers in pixels)"],"output_types":["cropped image file (PNG, JPEG, or original format)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_5","uri":"capability://image.visual.gaussian.blur.and.edge.preserving.image.smoothing","name":"gaussian blur and edge-preserving image smoothing","description":"Applies Gaussian blur filters to images using OpenCV's GaussianBlur function with configurable kernel size and sigma parameters, enabling AI assistants to reduce noise, create visual effects, or prepare images for downstream analysis. The implementation supports both standard Gaussian blur and bilateral filtering for edge-preserving smoothing.","intents":["I need to reduce noise in an image before analysis","I want to create a blurred background or privacy-preserving effect","I need to smooth an image while preserving edges for better detection"],"best_for":["AI assistants preprocessing images for analysis","developers building image enhancement pipelines","teams creating privacy-preserving image transformations"],"limitations":["Excessive blur (large kernel sizes) can remove important details needed for downstream tasks","Blur parameters (kernel size, sigma) require tuning for specific use cases — no automatic optimization","Processing time increases with kernel size and image resolution"],"requires":["Python 3.9+","OpenCV library","Valid image file path or URL","Blur parameters: kernel_size (odd integer), sigma (float)"],"input_types":["image file path","image URL","base64-encoded image","blur parameters: kernel_size, sigma"],"output_types":["blurred image file (PNG, JPEG, or original format)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_6","uri":"capability://image.visual.flood.fill.color.replacement.and.region.painting","name":"flood-fill color replacement and region painting","description":"Fills connected regions of similar color with a specified color using OpenCV's floodFill function, enabling AI assistants to replace backgrounds, paint regions, or modify specific color areas identified by analysis. The capability supports configurable color tolerance thresholds to control fill boundaries.","intents":["I need to replace a background color with a different color","I want to paint a specific region identified by color analysis","I need to fill transparent areas or remove unwanted color regions"],"best_for":["AI assistants performing background replacement workflows","developers building image editing automation","teams creating image preprocessing pipelines"],"limitations":["Flood fill works only on connected regions of similar color — fragmented or gradient backgrounds may require multiple fill operations","Color tolerance threshold must be tuned for specific images — too low misses similar colors, too high fills unintended regions","Performance degrades on very large images or images with many color variations"],"requires":["Python 3.9+","OpenCV library","Valid image file path or URL","Fill parameters: seed point (x, y), fill color (RGB), tolerance threshold"],"input_types":["image file path","image URL","base64-encoded image","fill parameters: x, y (seed point), color (RGB tuple), tolerance"],"output_types":["filled image file (PNG, JPEG, or original format)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_7","uri":"capability://image.visual.parametric.image.resizing.with.aspect.ratio.control","name":"parametric image resizing with aspect ratio control","description":"Resizes images to specified dimensions using OpenCV's resize function with support for multiple interpolation methods (bilinear, bicubic, Lanczos), enabling AI assistants to scale images for different use cases while controlling quality vs performance tradeoffs. The capability supports both absolute dimensions and aspect-ratio-preserving scaling.","intents":["I need to resize an image to fit specific dimensions for display or processing","I want to scale an image while preserving aspect ratio","I need to optimize image size for faster processing or storage"],"best_for":["AI assistants preparing images for downstream models with fixed input sizes","developers building image preprocessing pipelines","teams optimizing image storage and transmission"],"limitations":["Upscaling images beyond original resolution causes quality loss and artifacts — interpolation methods have limits","Downscaling loses detail — information cannot be recovered","Interpolation method selection affects quality and performance — no automatic optimization"],"requires":["Python 3.9+","OpenCV library","Valid image file path or URL","Resize parameters: target width, target height, interpolation method"],"input_types":["image file path","image URL","base64-encoded image","resize parameters: width, height, interpolation_method (bilinear/bicubic/lanczos)"],"output_types":["resized image file (PNG, JPEG, or original format)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_8","uri":"capability://image.visual.rotation.and.perspective.transformation.of.images","name":"rotation and perspective transformation of images","description":"Rotates images by specified angles and applies perspective transformations using OpenCV's warpAffine and warpPerspective functions, enabling AI assistants to correct image orientation, straighten skewed documents, or apply geometric transformations. The capability handles rotation around custom pivot points and supports configurable background fill for rotated areas.","intents":["I need to rotate an image to correct orientation","I want to straighten a skewed document or photo","I need to apply perspective correction to an image"],"best_for":["AI assistants preprocessing document images for OCR","developers building image correction pipelines","teams automating document scanning workflows"],"limitations":["Rotation creates empty areas at corners that must be filled — background color selection affects output quality","Large rotations (> 45 degrees) may create significant empty areas and quality loss","Perspective transformation requires accurate point correspondence — manual specification is error-prone"],"requires":["Python 3.9+","OpenCV library","Valid image file path or URL","Rotation parameters: angle (degrees), pivot point (optional), background color"],"input_types":["image file path","image URL","base64-encoded image","rotation parameters: angle, pivot_x, pivot_y, background_color"],"output_types":["rotated/transformed image file (PNG, JPEG, or original format)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-imagesorcery-mcp__cap_9","uri":"capability://image.visual.hue.saturation.value.color.space.manipulation","name":"hue-saturation-value color space manipulation","description":"Modifies image colors by adjusting hue, saturation, and brightness in HSV color space using OpenCV's cvtColor and in-place array operations, enabling AI assistants to perform color grading, desaturation, or color-based filtering. The capability converts between RGB and HSV, applies adjustments, and converts back while preserving image structure.","intents":["I need to adjust image brightness or contrast","I want to desaturate an image or convert to grayscale","I need to shift hue or adjust color intensity for visual effects"],"best_for":["AI assistants performing image enhancement and color grading","developers building image preprocessing pipelines","teams creating visual effects or color-based filtering"],"limitations":["HSV adjustments can produce unnatural colors if parameters are extreme","Color space conversion adds computational overhead compared to direct RGB manipulation","Results depend on original image color distribution — adjustments may not be uniform across different image types"],"requires":["Python 3.9+","OpenCV library with HSV support","Valid image file path or URL","Color adjustment parameters: hue_shift, saturation_factor, brightness_factor"],"input_types":["image file path","image URL","base64-encoded image","color parameters: hue_shift (0-180), saturation (0-2), brightness (0-2)"],"output_types":["color-adjusted image file (PNG, JPEG, or original format)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":28,"verified":false,"data_access_risk":"high","permissions":["Python 3.9+","FastMCP framework installed","YOLO model weights pre-downloaded via post_install.py script","OpenCV library for image I/O and preprocessing","Sufficient disk space for model weights (minimum 500MB)","CLIP model weights pre-downloaded via download_clip.py script","PyTorch or ONNX runtime for embedding computation","Minimum 4GB RAM for model loading, 8GB+ recommended","FastMCP framework integration","OpenCV library with alpha blending support"],"failure_modes":["YOLO detection accuracy varies by model size (nano/small/medium/large) — larger models are slower but more accurate","Requires GPU or significant CPU resources for real-time performance on high-resolution images","Model weights are large (50-200MB depending on variant) and must be downloaded during post-installation setup","Detection performance degrades on images with extreme lighting, occlusion, or out-of-distribution objects","CLIP performance depends on label specificity — vague descriptions produce lower-quality results","Embedding computation is slower than traditional classifiers (typically 100-500ms per image on CPU)","Model weights are large (1-5GB depending on variant) and require significant memory during inference","Cross-lingual and domain-specific performance may be limited depending on training data coverage","Overlay positioning requires manual specification — no automatic alignment or content-aware placement","Blending quality depends on image formats and alpha channel support — JPEG overlays may have artifacts","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.35,"ecosystem":0.39999999999999997,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:03.041Z","last_scraped_at":"2026-05-03T14:00:15.503Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=imagesorcery-mcp","compare_url":"https://unfragile.ai/compare?artifact=imagesorcery-mcp"}},"signature":"LVaenTSvVU2UP5T0IYaZX5udLfS+9M0Cxfg14vVjlu0kQ7FrFdbHcXdA3o/O/JnvW3n6BrEJbHJft6FpEtYgCg==","signedAt":"2026-06-21T13:43:53.833Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/imagesorcery-mcp","artifact":"https://unfragile.ai/imagesorcery-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=imagesorcery-mcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}