MCP directory
Media
582 MCP servers — install commands + config snippets + live GitHub stats. Browse anonymously, or sign in to like, install, and tune your For You feed.
-
EverArt
AI image generation via the EverArt API — text-to-image with multiple model choices.
npm install -g @modelcontextprotocol/server-everart - Community Media
OpenAI Images
Generate + edit images via DALL-E 3 + gpt-image-1 — straight pipe to the OpenAI image API.
uvx openai-images-mcp -
Replicate
Run any model hosted on Replicate — image, video, audio, language — via one tool surface.
npm install -g mcp-replicate -
YouTube Transcript
Pull the transcript + chapter timestamps of any YouTube video — no API key required.
npm install -g @kimtaeyoon83/mcp-server-youtube-transcript - Community Media
Whisper Transcribe
Transcribe audio files locally via Whisper — runs whisper.cpp under the hood.
uvx mcp-whisper - Community Media
Fal.ai
Run any model hosted on Fal.ai — fast inference for FLUX, SD, video, audio.
npm install -g mcp-fal -
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
go install github.com/.../localai@latest -
godot-mcp-pro
162 MCP tools for AI-powered Godot 4 development. Scene, animation, 3D, physics, particles, audio, shader, input simulation, runtime analysis, navigation, testing & more. $15 one-time.
# See README at the repo for install instructions -
flux-operator
GitOps on Autopilot Mode
go install github.com/.../flux-operator@latest -
voicemode
Natural voice conversations with Claude Code
uvx voicemode -
xiaozhi-esp32-server-java
小智ESP32的Java企业级管理平台，提供设备监控、音色定制、角色切换和对话记录管理的前后端及服务端一体化解决方案
# See README at the repo for install instructions