MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
puppetry-sdkgithub.com/puppetry-ai/puppetry-sdkupdated this year
Turn a photo + script into a talking-head AI video. TypeScript SDK & MCP server for Claude, OpenAI Codex, and Cursor.
-
Router skill for talking-head video: preflight the portrait + audio, then route to the right backend (free local SadTalker, rented-GPU SadTalker, Hedra API, HeyGen API). Zero-dependency tool, Cursor rule, MCP server.
MIT -
mcp-avatargithub.com/kevinten-ai/mcp-avatarupdated this year
MCP server for AI digital human / talking head video generation. Photo-to-video with voice sync.
MIT -
com.puppetry/mcp-serverno update data
Turn a portrait photo and a script into a talking-head AI video via the Puppetry API.
npm -
Brollss MCP plugin for Claude Code, Cursor and Codex: edit talking-head videos from your agent.
Apache-2.0 -
@askeditor/mcpactive
Cut bad takes out of a talking-head recording from your own editor, over an issued AskEditor API key
npm SEE LICENSE IN LICENSE -
AI Capcut MCP server for automated "talking head" video processing. Removes pauses, detects duplicate takes, adds subtitles — and exports to CapCut project.
MIT ★ 126 -
ai-video-editorgithub.com/timkulbaev/ai-video-editorupdated this year
CLI tool that auto-edits talking-head videos: removes silences, filler words, and restart phrases using Silero VAD + faster-whisper. MCP server for Claude Desktop included.
MIT ★ 14 -
Set up and watch a one-person talking-head shot with a Sony FX30 and an amaran light, from Claude Code (MCP)
MIT -
Local macOS video editor for shorts and talking-head videos: transcript cuts, ranking shorts, versioned edit styles, yt-dlp downloads, CC0 SFX packs, YouTube scheduling and an MCP server for AI agents.
MIT -
Command-line tools and MCP server for MaGiK Studio: AI photo tools (upscale, retouch, cutout, fill, erase and more) and video tools (talking heads, AI films, captions, dubbing, short clips, eye contact, scripts).
npm MIT -
Open-source CLI that cuts ums, stutters, retakes and dead air from talking-head video. 39s first take → 17s clean cut.
MIT ★ 1 -
@socialaf/mcp-servergithub.com/socialaf/socialafupdated this year
MCP server for socialAF Character Studio. Build characters, generate images, video, voiceovers, and lip-synced talking heads from any MCP client (Claude Desktop, Cursor, OpenClaw, etc.).
npm MIT -
Let your AI make the video. Declarative video for engineers: a script plus a taste profile render to MP4, with cuts that land on the beat and talking-head takes composited in.
npm AGPL-3.0-only -
Voice to structured notes and diagrams. Talk, and a local model builds the headings, lists, tables and diagrams while you think, then typesets a PDF. Hands-free or one-handed with an MCP toolbox for AI agents.
MIT ★ 6 -
Takes for Mac (gettakes.app): a free, open-source Mac app for talking-head videos. A teleprompter that follows your voice, camera and screen recording, and your agent (Claude Code, Codex or pi) writes the script, cuts the edit and drafts the posts through the takes MCP server. Apple silicon, macOS 15+. Shared as is.
mcpb MIT ★ 40 -
higgsfield-mcpgithub.com/storyvord/higgsfield-mcpupdated this year
MCP server for Higgsfield AI cinematic image and video generation
npm MIT -
@xuxuanming/mcp-connectoractive
大猫剪辑(DaMao Video)WorkBuddy MCP 连接器 — 把本机大猫剪辑客户端的 automation API 封装为 MCP 工具(数字人视频 / 真人口播视频 / 资产管理 / 任务跟踪)
npm UNLICENSED -
LiveAvatarStream3Dgithub.com/tech-sumit/LiveAvatarStream3Dupdated this year
🎬 Browser-based 3D talking-avatar studio — write a script, a lip-synced 3D presenter delivers it, export MP4 client-side with WebCodecs. Direction as data. Agent-native via WebMCP. No render server.
MIT ★ 2 -
MCP server + skills that let your AI coding agent (Codex / Claude Code) drive Pireel Studio — cut by transcript, storyboard, caption and design videos right from chat.
Apache-2.0 ★ 13