Media

智谱 GLM Coding Plan 视觉理解 MCP Server，对标官方 @z_ai/mcp-server

Official Zvid MCP server — render videos & images from JSON and manage templates, projects, webhooks and credits, from Claude, Cursor, Codex, n8n or any Model Context Protocol client.

Hosted media & study tools for AI agents: transcribe audio/video to text + SRT/VTT (Whisper large-v3), summarize recordings, generate study notes and flashcards, answer questions about documents with citations, and compress PDFs. No API key required.

URL -> design tokens -> DESIGN.md. The extraction engine.

MCP server for SaluteSpeech — speech recognition and synthesis (Russia)

AtlasCloud CLI for calling LLM, image, video, and audio APIs from terminals, scripts, and CI jobs.

MCP server for the SonoVault music metadata API. Search 93M+ tracks, artists, and releases; get genre, label, release dates, ISRC/ISWC codes, and cross-platform IDs.

Turn a video (bug report, screen recording) into an agent-readable set of annotated keyframes. CLI + MCP server; the only native dependency is ffmpeg.

RunAPI Flux MCP server for image generation: create tasks, poll results, and check pricing across 3 model variants from Claude Code, Codex, Cursor, and VS Code.

Autonomous AI video editor over MCP: viral clips, captions, reframe, chroma key, MP4 export

Provider-neutral agent runtime for coding workflows. Verified DAG execution with evidence gates, worktree isolation, and local graph memory.

MCP server for Genesis UI Design System - provides AI assistants with access to components, hooks, and design tokens

Language expression wizard with audio - MCP server for Claude Code

Topaz Labs MCP server — AI image enhancement for LLMs

MCP server for the PicDefense.io API — image risk scoring, EXIF, reverse-image backlinks, and image content detection (face, landmark, logo, label, SafeSearch)

MCP server + CLI for uiscanner: scan any public URL for a design teardown (tokens + section structure + a Claude-tailored build prompt).

ShotFlow MCP Server — AI分镜脚本与视频生成智能体，支持生成专业分镜、视频、镜头重生成、配额查询等能力。

Comfy Agent is a tool to use ComfyUI from the CLI. It is suitable for both direct CLI usage and AI-agent-driven automation.

MeshGenie generation MCP — ask your coding agent for a rigged, animated game character and get a GLB in your project.

MCP server for ELYTH - enables AI agents to interact with the ELYTH AITuber social platform