mcp.film / Avatars & Performance / Tavus MCP
Tavus MCP
Phoenix replicas, persona videos, lipsync, and conversational AI via the Tavus API.
What it does
Comprehensive community MCP server exposing 25 tools across the full Tavus API: Phoenix replica (digital twin) training, persona management, video generation, real-time conversational video (CVI), lipsync, and speech synthesis. Tavus now ships a first-party MCP too, but it covers only conversational-agent configuration — for replica training, video generation and lipsync this is still the only MCP that reaches them.
Connect
Connection is set up through the vendor's flow — follow the official connect instructions.
Local install: Build from source: clone rakeshdavid/Tavus-MCP, npm install && npm run build, then run node build/index.js with TAVUS_API_KEY. Smithery is the documented alternative: npx -y @smithery/cli install @rakeshdavid/tavus-mcp --client claude
TAVUS_API_KEY — https://platform.tavus.io
Sample tools
create_replicagenerate_videocreate_conversationcreate_personacreate_lipsyncgenerate_speechField notes
The official server keeps growing and still does not reach what this one does. Tavus's first-party MCP is hosted at https://mcp.tavus.io/mcp (`claude mcp add -s user --transport http tavus https://mcp.tavus.io/mcp`, browser OAuth, no key in your config) or local via `uvx --from 'tavus-cli[daily]' tavus-mcp`; PyPI tavus-cli is at 0.11.0 as of 21 Oct 2026, up from 0.4.3 in August. Its tools reference now lists 81 tools, and they are still about configuring PALs — prompts, objectives, guardrails, knowledge, pronunciation dictionaries, deployments, live preview conversations. Faces can be listed (tavus_face_list) but not trained, and nothing renders a video file or runs lipsync. That is a conversational-agent product, which is why it is not listed here separately and this server still is. What you are living with, re-confirmed 23 Oct 2026: the README's npm package (tavus-mcp) is still not on npm — the registry 404s — so install from source or via Smithery; the repo has had no commit since 2025-07-09 and holds 2 stars, so treat it as unmaintained rather than quiet; it is built on an old MCP SDK version. Tavus free developer plan: ~25 min conversational video + 5 min generation.
Also in Avatars & Performance
Hosted MCP for avatar videos, lipsync, and 175-language video translation.
Character-3 talking-avatar video, TTS, and image generation through Hedra's API.
Official CraftStory server: talking-avatar video from a photo and audio, plus short MiniMax H3 clips with sound.
Official bitHuman CLI server: build avatar agents from a face image and render WAV-driven talking video locally.
Official Sync MCP for lipsync generation, voice cloning, and TTS on existing footage.
D-ID's hosted MCP connecting agents to the D-ID API and docs for avatar video.
Used in
Create avatar, talking-head, or UGC-style video
Pairs well with
Official hosted Artlist MCP — generate images, video, music and voice-over on your Artlist credits.
Hosted OAuth MCP onto BudgetPixel's image, video, music, SFX and Topaz upscale catalogue.
Hosted screenplay-to-production MCP with free planning and quotes, then a greenlit run under a server-enforced cap.