Image, audio and video generation and processing.
Multi-host plugin for delegating tasks and code reviews to Google Antigravity CLI (agy). Works inside Claude Code, Codex CLI, agy itself, and as a standalone CLI.
MCP server for generating deterministic PlacePack placeholder image URLs and packs.
AITuber MCP server, hosted at https://mcp.aituber.app. Create AI videos with narration, visuals, and captions, then publish to YouTube, TikTok, Instagram, Facebook, Threads, and X from Claude Desktop, Claude Code, ChatGPT, Codex, Cursor, or OpenClaw.
UI structure extractor for text-only LLMs - pure Go binary, offline, CGO_ENABLED=0, MCP-native
MCP server that screenshots a live URL and diffs it against a static design image (PNG/JPG), returning grouped diff regions with severity scores. Deterministic capture: animations disabled, fonts fully loaded, fixed locale/timezone.
MCP server exposing OpenAI's gpt-image-2 for image generation and iterative editing.
Vivijure Studio MCP: drive the film studio API (vivijure-cf / vivijure-local) and optionally the hosted control plane admin API from an agent.
MCP server for Z.AI image generation models (GLM-Image, CogView-4)
MCP server supporting multiple AI providers for image generation - OpenAI, Stability AI, Replicate, HuggingFace
MCP server for image generation using Google Gemini AI
MCP server for Venice AI - chat, images, TTS, embeddings, and account management
MCP server exposing NaN API tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank
Local-first Figma MCP server. Full read-side parity with the official Figma MCP on free plans, HTML 1:1 replica tooling with three-gate parity verification, and write-to-canvas via a companion plugin bridge.
Unofficial MCP server for cosmos.so. Search, browse and build visual moodboards with Claude, Cursor or any MCP client.
Sound effects for AI agent hooks. Pick a sound for TaskCompleted, PostToolUse and friends from a local web UI.
Model Context Protocol server for swatchbook — exposes a DTCG project's tokens, axes, and diagnostics to AI agents without running Storybook.
MCP server that gives any text-only LLM vision — image analysis, OCR, comparison, region zoom, and video frame analysis.
Approval-gated stdio MCP server for Smart UI generation, deterministic validation, bounded implementation handoff, reports, and governed memory.
MCP server fronting the Miadi voice layer with episode addressing — play, find, publish and mint episode-bound voice from an agent's tool surface.
AI rap songs about today's headlines in any rapper's style. Free trial + x402 payments.