Media

Tavus MCP Server

Connect your account, then chat with AI to run tools.

Train photorealistic faces, configure PAL personas, render personalized videos, and launch real-time conversational video sessions from chat.

Best forSalesCustomer SuccessMarketing AutomationL&D

Try this workflow

Inventory faces and personas

List my Tavus replicas and personas, summarize training status on each face, and note which persona ids have a default replica configured.

Start chatting
Managed
13 tools
Agent guide included

Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.

Browse all tools

What you can do with Tavus

Built for

Sales Teams, Customer Success, Marketing Automation, L&D Teams, AI Product Builders

Example workflows

Inventory faces and personas

Grounds later video or conversation creation in live account inventory.

Try this

List my Tavus replicas and personas, summarize training status on each face, and note which persona ids have a default replica configured.

Check rendered video status

Typical post-generation workflow before sharing a personalized clip.

Try this

List my recent Tavus videos, pick the newest generating or ready entry, and tell me whether a download link is available yet.

Review conversation sessions

Operators monitoring live CVI sessions without opening the Tavus dashboard.

Try this

List my Tavus conversations from the last page, show active vs ended counts, and summarize join URLs for any still-active sessions.

Plan a personalized outreach clip

Connects read-only catalog discovery to a concrete video brief.

Try this

From my Tavus replica and speech catalog, recommend which face and script pairings fit a short renewal reminder video.

Context to know first

What can AI agents do with Tavus on MCPBundles?

Agents can list or fetch personas, replicas, speeches, videos, and conversations; create conversations and rendered videos; update persona settings and video names; and delete personas, replicas, videos, or conversations when asked.

How do I connect Tavus to MCPBundles?

Add your Tavus API key from the Tavus developer settings on MCPBundles. The platform stores the key securely and sends it on each Tavus request.

What is the difference between a Tavus conversation and a video?

Conversations are live real-time CVI sessions with join URLs. Videos are asynchronous rendered clips from a replica plus script or audio — poll status until ready before sharing download links.

AI Skill
SKILL.md

Domain knowledge for Tavus — workflow patterns, data models, and gotchas for your AI agent.

Tavus

Tavus builds personalized video and real-time conversational video (CVI). Modern API terms are PAL (behavior, prompts, pipeline) and Face (photorealistic likeness). Legacy names persona and replica still work on the same endpoints.

Data Model

  • Personas (PALs) — behavior, system prompt, default face, and pipeline layers for live conversations.
  • Replicas (Faces) — photorealistic likenesses trained from sample video or image; async training.
  • Speeches — script catalog for rendered video generation (list-only upstream surface).
  • Videos — rendered outputs from a replica plus script or audio URL.
  • Conversations — live CVI sessions pairing a PAL with a face; returns join URLs and status.

Operational order

  1. List personas and replicas to discover ids before creating conversations or videos.
  2. For rendered video, pick a replica id and either a speech script or your own script text.
  3. For live CVI, start a conversation with face_id and pal_id (or a PAL that already has a default face).
  4. Poll video status on single-video reads until status is ready before sharing download links.
  5. Prefer ending finished conversations for routine cleanup; reserve delete for destructive removal.

Gotchas

  • Replica training is async: New replicas return training status — wait for completed before use.
  • Persona + replica pairing: Conversations need a valid face; PALs may supply default_replica_id.
  • Pagination: List reads accept page and limit; follow total_count and page through results.
  • Speeches are catalog-only: No create/update/delete on the speech list — scripts come from the catalog response.
  • test_mode on conversations: Validates payload without a billable PAL join when testing integrations.

Tools in this Server (13)

Tavus Delete Conversation

Permanently delete a Tavus conversation and associated data by id. Destructive and idempotent. Pass hard=true only when irrevocable removal is intende...

Tavus Delete Persona

Permanently delete a Tavus persona (PAL) by id.

Tavus Delete Replica

Delete a Tavus replica (face) by id. Deleted replicas cannot be used in new conversations or videos.

Tavus Delete Video

Delete a rendered Tavus video by id. Pass hard=true only when irrevocable asset removal is intended.

Tavus Get Conversations

List or fetch Tavus real-time video conversations (CVI sessions). Omit id to page through conversations; pass id for one session including join URL, s...

Tavus Get Personas

List or fetch Tavus personas (PALs) that define behavior, prompts, and default faces for conversational video. Omit id to list; pass id for one person...

Tavus Get Replicas

List or fetch Tavus replicas (photorealistic faces) used in videos and live conversations. Omit id to list training status and thumbnails; pass id for...

Tavus Get Speeches

List speech scripts available in your Tavus account for personalized video generation. The upstream speech catalog is list-only; pick a script id from...

Tavus Get Videos

List or fetch Tavus rendered videos. Omit id to page through generation status, scripts, and download links; pass id for one video including ready-sta...

Tavus Upsert Conversation

Start a new real-time Tavus video conversation. Creation only — pass face_id and pal_id (or a PAL with a default face). Returns conversation_id, join ...

Tavus Upsert Persona

Create or update a Tavus persona (PAL). Omit id to POST a new persona — requires pal_name and system_prompt unless using echo pipeline mode. Pass id t...

Tavus Upsert Replica

Create a Tavus replica (face) from training media. Creation only — training is asynchronous. Provide train_video_url or train_image_url (with voice_na...

Tavus Upsert Video

Create a rendered Tavus video or rename an existing one. Omit id to POST a new video — requires replica_id and either script or audio_url. Pass id wit...

Frequently Asked Questions

What can AI agents do with Tavus on MCPBundles?

Agents can list or fetch personas, replicas, speeches, videos, and conversations; create conversations and rendered videos; update persona settings and video names; and delete personas, replicas, videos, or conversations when asked.

How do I connect Tavus to MCPBundles?

Add your Tavus API key from the Tavus developer settings on MCPBundles. The platform stores the key securely and sends it on each Tavus request.

What is the difference between a Tavus conversation and a video?

Conversations are live real-time CVI sessions with join URLs. Videos are asynchronous rendered clips from a replica plus script or audio — poll status until ready before sharing download links.

Why is my new replica not usable yet?

Replica training is asynchronous. New faces stay in started status until training completes; list or fetch the replica row again before starting conversations or videos.

How do I connect Tavus to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/tavus. Authentication is handled automatically.

How many tools does Tavus provide?

Tavus provides 13 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Tavus require?

Tavus uses API Key. Tavus requires credentials. Connect via MCPBundles and authentication is handled automatically.

Setup Instructions

Connect Tavus to any MCP client in minutes

MCP URL
https://mcp.mcpbundles.com/bundle/tavus
Claude.aiCursorVS CodeVS Code InsidersGooseLM StudioCherry StudioChatGPT

One-click install:

Install on Claude.aiInstall for organization (admins)

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

  1. Open claude.ai → Settings → Connectors.
  2. Click the + button and choose Add custom connector.
  3. Set Name to Tavus and paste the MCP URL into Remote MCP server URL.
  4. Click Add. Tavus will appear under Not connected — select it and click Connect to complete OAuth.
Name: Tavus
Remote MCP server URL: https://mcp.mcpbundles.com/bundle/tavus
Authentication: OAuth

Custom connectors at claude.ai require a paid Claude plan (Pro, Max, Team, or Enterprise).

Related MCP Servers

More media integrations you might like

Image Edit

Deterministic pixel editing — crop, exposure, saturation, sharpen, resize, and format convert. Host ...

7 tools
Media
Remove.bg

Remove.bg automatically removes backgrounds from images using AI. Upload an image and get back a tra...

2 tools
Media
Pexels

Pexels API is a developer tool providing access to a large library of free stock photos and videos, ...

3 tools
Media
Plaud

Plaud is a hardware-and-AI voice recording platform (Plaud Note, Plaud NotePin). This MCP reads your...

8 tools
Media
AssemblyAI

AssemblyAI offers a Speech-to-Text API, providing automated transcription and audio intelligence fea...

5 tools
Media
MusicBrainz

MusicBrainz is an open music encyclopedia that collects music metadata and makes it available to the...

31 tools
Media

Ready to use Tavus?

Sign in to connect your credentials and start running tools from the chat.

Tavus MCP Server — Personalized & Conversational Video for…