"JPEG" matching MCP servers:

media-gen renders Claude-authored content — SVG markup, HTML documents, or a JavaScript canvas draw() function — into PNG/JPEG/WebP images and MP4 video using headless Chromium and ffmpeg, with no API keys required. It also offers an optional bring-your-own-key path for photorealistic text-to-image and text-to-video generation via OpenAI, Gemini, or fal.ai.

A local stdio MCP server for generating images using Google's Gemini image models, saving to disk as JPEG.

On-demand live vision MCP for AI agents — open a session at a lat/lng, receive a JPEG snapshot or WebRTC stream, settled per-second in USDC on Base. Four tools (get_session, get_frame, get_stream_url, cancel_session); currently Base Sepolia testnet.

Enables converting images (JPEG, PNG, GIF, WebP) into text descriptions using OpenAI-compatible vision models, with support for both local files and URLs.

Gives MCP clients a suite of AI photo-editing and design tools — background removal, upscaling, object/watermark erasing, sky and background replacement, retouching, generative fill — along with multi-layer design composition and rendering to PNG, JPEG or PDF. Every call is proxied with an API key to the snapnedit API, so no models run locally.

Exposes seven tools that turn Azure cost-pattern and AI FinOps analysis into drafted optimization plans, with human approval bound to a SHA-256 digest and dry-run execution recorded in a hash-chained audit log. Deliberately ships no approve tool, so nothing can be changed in the estate without people signing off first.

AI-agent image generation: cohesive image sets and single illustrations over MCP. PNG/WebP (optional transparency) or JPEG.

Enables MCP clients to generate images from text prompts and edit existing PNG/JPEG files with natural-language instructions by driving a local ComfyUI instance running Qwen Image models. Supports aspect ratios, exact pixel dimensions, batch counts, and reproducible seeds, with matching capabilities exposed through a Python CLI.

Define one master style once (lighting, mood, composition, colour) and generate unlimited matching images with different subjects. Hosted remote MCP at https://imag8.art/api/v1/mcp with tools imag8_generate_image, imag8_suggest_variations, imag8_get_account_status. Works with Claude, Cursor, ChatGPT and custom agents. Free tier: 10 credits/month.