AI and Machine Learning Servers

Generates images using Google's Gemini 2.5 Flash model and automatically uploads them to ImgBB, returning publicly accessible URLs for immediate web sharing without local file management.

Integrates with Perspective API to analyze text toxicity and provide content moderation across multiple languages for enhanced online safety.

Integrates with ModelScope's Qwen-Image model to generate images from text prompts, returning base64-encoded results with automatic format detection and error handling for multilingual content creation.

Enables AI assistants to generate images through the Grok2 model using stdio transport for seamless integration into existing workflows.

Provides a server for obtaining structured and freeform code reviews from OpenAI, Google, and Anthropic models with support for project context, related files, and language detection.

Detects search intent for SEO-related workflows.

Extracts content from diverse media sources including URLs, documents, videos, audio files, and images using intelligent auto-detection and multiple extraction engines for unified content processing and analysis.

Provides dual-perspective analysis through alternating actor and critic viewpoints for evaluating creative works, strategic decisions, and complex scenarios requiring both empathetic understanding and objective assessment.

Provides a bridge between virtual try-on technology and clothing visualization, enabling users to see how selected items would look on them through image processing and metadata-rich clothing resources.

Transforms static images into animated Ghibli-style videos through the GPT4O Image Generator API with tools for credit balance checking and task monitoring.

Enables image generation from text prompts via OpenAI's API, returning the created image saved to a specified file path

Integrates with SVGMaker's API to generate SVGs from text descriptions, edit existing images, and convert bitmap images to vector format with customizable quality settings and real-time progress tracking.

Translates JSON internationalization files using multiple translation providers (Google Gemini, OpenAI, Ollama/DeepSeek) with intelligent caching, deduplication across files, and format preservation to minimize API costs while maintaining exact JSON structure and consistent results across target languages.

DeepL Translator

Official

Integrates with DeepL to provide high-quality text translation and rephrasing between numerous languages with formality controls for supported language pairs.

FindMine Shopping Stylist

Official

Integrates with FindMine's product styling API to enable fashion recommendations, outfit creation, product browsing, and style guide access for e-commerce platforms.

Provides image generation across multiple AI providers (OpenAI DALL-E, Google Gemini, Replicate Flux) with unified parameter handling, automatic file saving, and provider-specific features like transparent backgrounds and seed control for flexible visual content creation.

Connects AI systems to Qdrant vector database for semantic search capabilities through multiple embedding services, enabling efficient document management and similarity searches without leaving the conversation interface.

Processes Sketch design files by extracting internal structure, analyzing design elements, and rendering visual components as SVG images for design-to-code workflows and automated design analysis.

Integrates with HiveFlow's workflow automation platform to enable triggering automated workflows, managing business processes, and executing workflow operations directly through conversational interactions.

Unified platform that bridges REST API and MCP functionality, enabling assistants to interact with custom APIs through both HTTP endpoints and tools for image processing, web access, social media, and AI workflows.

Provides six specialized servers for scientific and engineering workflows including photonic circuit design with gdsfactory integration, document processing with advanced OCR, plot data extraction from images, equation composition and analysis, PDF annotation with contextual analysis, and model fitting with optimization capabilities.