"Mock Service Worker" matching MCP servers:

Enables private, GPU-backed image upscaling via a local Hermes MCP bridge that submits jobs to an authenticated Upscayl worker API.

MCP server deployed on Cloudflare Worker that provides AI with image understanding via the describe_image tool, plus an Apple-style model status dashboard.

MCP server for local AGY worker runtime, enabling controlled task execution with permission checks, evidence collection, and status tracking for build, browser, and image workflows.

MCP server that turns articles, transcripts, and markdown into LinkedIn carousel PDFs, Instagram PNGs, and Threads PNGs. Content in, slides out. No web UI, no cloud service.

Local stdio MCP service that calls GPT Image API to generate images from text, edit images with references or masks, and save images locally while returning absolute paths and file URIs.

Generates mock 2D PNG assets for game prototypes, supporting gradients, patterns, text, spritesheets, and embedded metadata.

Provides a catalog of paid micro-work tools for text processing, speech, and image generation with fixed USDC pricing via x402. Enables agents to discover capabilities, get quotes, and prepare calls without handling wallet keys.

MCP server for AI image generation supporting text-to-image and image-to-image editing via any OpenAI-compatible service, with configurable models, aspect ratios, and sizes.

Enables AI assistants to generate images from text prompts and transform existing images using Google Gemini's nano banana model through the Nanana AI service. Supports both text-to-image generation and image-to-image transformation capabilities.

Exposes local Umi-OCR v2 capabilities to AI agents via MCP, enabling image text extraction, batch OCR, PDF OCR, and status checks without manually starting the service.

A self-hosted server that lets users prepare marketplace listings from photos in ChatGPT, review a draft, and publish only after explicit confirmation, with mock and live modes.

A self-hostable MCP server that exposes Roshan AI's Alefba OCR service as tools, enabling document reading, page extraction, status polling, and export to PDF/Word/Excel for Persian, Arabic, and English text.

Enables local, upload-free analysis of publicly viewable videos through tools that pull metadata, chapter plans, platform subtitles or speech-to-text transcripts, sampled frames and contact sheets, 527-class sound event tags, and comment analysis. It downloads only the minimum necessary bytes, so users can inspect long videos section by section, job-poll lengthy runs, and check the local model/environment setup without sending media to any cloud service.

Enables AI-driven creation of savable Wallpaper Engine web wallpaper source projects through a local STDIO service, with bounded project discovery, revision-checked file edits, checkpoint restore, validation, and publish staging. It also opens managed preview windows to set public properties and capture screenshots and bounded logs as runtime feedback from the official engine.

Enables MCP clients to create and edit pixel-art sprites locally through a managed engine, including generation, editing, inpainting, rotation, listing outputs, and service status.

Enables AI agents to recognize and extract text from images using PaddleOCR, supporting both file paths and base64 input with structured results including confidence scores and text positions.

Enables Codex to delegate bounded code analysis, review, isolated edits, multimodal research, and native image generation to supervised Antigravity workers, with queued execution, retries, and inspectable patches.

Enables AI clients to generate Perchance images and manage user keys via a lightweight MCP server that fits in 512MB RAM by offloading browser-based Turnstile solving to an external solver service.

Enables an AI agent to list the incident categories of Gijón's municipal reporting system and file real service notices on a citizen's behalf, including generating one from a photo by reading its EXIF GPS and suggesting the matching category. Report creation is dry-run by default and only sends after explicit human confirmation, using a saved email as the contact identity and no credentials.

Provides tools for generating optimized images via Google's Gemini model and fetching weather forecasts and alerts from the National Weather Service. It enables users to create visual content and retrieve environmental data seamlessly within MCP-compatible clients.