Hosted MCP server (OAuth, no API keys) that makes short drama series (micro-dramas, sitcoms, K-drama style, any language) and other short vertical videos from Claude, ChatGPT or Codex, with the same cast every episode.
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.
Enables AI agents to draft social media posts for seven platforms, rewrite them to read as human-authored, score them against AI detection, and optionally generate matching images.
Enables MCP-capable chats and agents to generate images, video, and audio through OpenAI, Google Gemini, fal.ai, and Cloudflare Workers AI, optionally routed via Cloudflare AI Gateway. Supports image editing, asynchronous video jobs, and text-to-speech with per-request provider and model overrides, and can run over stdio or streamable HTTP.
Enables AI image and video generation using Google Nano Banana and Veo 3.1 via a LiteLLM gateway, providing tools for synchronous image generation and asynchronous video generation with polling, returning public URLs.
Enables image and video generation across GPT-Image, Gemini, Grok, and Jimeng with file-based outputs, multi-reference support, and model capability lookup.
Enables generating images, video, and audio through a single capability-oriented interface, with server-side routing, safety screening, job lifecycle management, concurrency limits, and retention.
Lets Claude Desktop and Claude Code generate images, videos, speech, and music through any Poe bot using a Poe API key, downloading the resulting media to local files and returning their paths along with the original URLs.
Enables MCP clients such as Claude to generate and edit images with Google's Nano Banana models and create videos with Gemini Omni Flash, while enforcing cost limits, sandboxed file access, no-overwrite outputs, and provenance sidecars.
Enables AI coding clients to generate and save project-aware images and videos using existing paid AI subscriptions, without API keys or passwords, and to optimize media for the web.
Enables Claude Code, Cursor, Codex and other MCP clients to generate and edit images and videos directly in a project using AI subscriptions the user already pays for, without API keys or extra billing. Also provides local media tools such as background removal, video editing for social formats, and automatic resizing and optimization of results.
MCP server for generating and editing images using OpenAI, and creating videos using OpenAI Sora and Google Veo. Enables fetching media from URLs or disk with smart output placement.
Enables Claude Desktop, Claude Code, and Cursor to generate and transform photorealistic images, remove backgrounds with alpha matting, stage products in commercial scenes, and batch-render catalog assets through native MCP tools.
Provides tools for agent-driven video creation, including image generation via Google's GenAI, video generation, and local video stitching with FFmpeg.
A remote MCP server that lets Claude generate and edit images, start short videos, produce speech, and transcribe audio through xAI's media models, returning previews and files for review. It enforces per-call, per-session, daily and monthly spend caps behind owner-only OAuth access, with content tripwires that refuse unsafe prompts.
Enables text-only coding models to read images, PDFs, presentations, spreadsheets, and other non-text files through a single analyze_media tool, combining local document extraction, OCR, and optional vision models with clear evidence labeling.
MCP server that enables AI assistants to generate images and videos on demand using free-tier providers like Agnes AI, Cloudflare Workers AI, Hugging Face, and Google Gemini, with tools for creating media, polling async jobs, and listing providers.
Enables local video and audio understanding by measuring duration, codecs, silence, black or frozen frames, loudness and audio peaks with FFmpeg, and by sending only a trimmed clip range to an OpenRouter model for detailed chronological summaries or focused questions. Runs entirely on local files with no Codex fork required.
Enables MCP clients to generate images and videos across 40+ providers using their own API keys, compare provider prices before spending, and save every result to a searchable local library for reuse and chaining.
Enables room agents to generate or edit images (published directly into the room's Docs rather than passed through the model's context) and transcribe audio attachments, using the deployment's media providers with the room itself acting as the credential.