Images, Video & Audio MCP servers
Image, video, audio, speech, and design-tool servers.
Audio File MCP App
Inspect local audio files — playback, metadata, loudness, spectrogram.
gemini-image
Google Gemini image generation, editing, and local processing via MCP
muapi
Generate images, videos, and audio using 100+ AI models via muapi.ai.
The Game Crafter
Design, manage, and price tabletop games on The Game Crafter via MCP.
Glif
RemoteGenerate images, video, and audio with Glif's media-generation agent
ShortPixel Image Optimizer
RemoteOptimize public image URLs via the ShortPixel SPIO API for AI agents
vibemovie
Turns an agent coding session into a short recap video. Local-first.
ClipGrab
Save the system clipboard image to a PNG or JPG file for AI agents.
mermaid-render-mcp
Renders Mermaid diagram syntax to PNG or SVG images for LLM clients
yutu
The AI-powered toolkit that grows your YouTube channel on autopilot
APICK Vision
RemoteImage/video analysis: NSFW detection, object detection, thumbnails
gimp-mcp
Control GIMP image editing via Python-Fu scripting from AI agents.
reMarkable MCP Server
Read, render, search, and manage reMarkable documents through MCP
viberadio-fm
Turns an agent's output into audio: narration, podcast, or music.
figma-edit-mcp
Programmatically read, create, and modify Figma designs via MCP.
PodMule
RemoteSearch, draft and manage your podcast workspace from your agent.
voicemode
Natural voice conversations for AI assistants - STT/TTS via MCP
gpt-image-2-polza-mcp-server
GPT Image 2 MCP server backed by Polza media and storage APIs.
Pdfrender
RemoteHTML-to-PDF MCP server — render pixel-faithful PDFs from HTML.