Tavus Video Replicas MCP. Generate talking-head videos from scripts and clones.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Tavus Video Replicas manages personalized AI video content. This server lets your agent list, inspect, and delete trained video clones (replicas).
You can then generate new videos by providing a script and selecting a replica, all from natural language commands.
What your AI agents can do
Delete replica
Permanently deletes a specific, trained AI video replica.
Delete video
Removes a generated video file from the content library.
Generate replica video
Creates a new talking-head video by using a specified replica and input script.
Create new personalized talking-head videos by inputting a script and specifying which AI replica to use.
List all trained video replicas or retrieve detailed information about a specific clone's settings.
Check the live progress of any video generation task to confirm when the content is ready for download.
Get a list of all your generated videos and their associated download links in one call.
Permanently delete specific video files or trained replicas to clean up unused storage.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Tavus Video Replicas MCP Server: 7 Tools for Video Ops
These tools let you manage the entire lifecycle of AI-generated videos, from listing clones to generating and deleting final assets.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Tavus Video Replicas on Vinkius019d8488delete replica
Permanently deletes a specific, trained AI video replica.
019d8488delete video
Removes a generated video file from the content library.
019d8488generate replica video
Creates a new talking-head video by using a specified replica and input script.
019d8488get replica details
Retrieves comprehensive data about a single, specific AI video replica.
019d8488get video details
Gets detailed information for one generated video asset.
019d8488list generated videos
Returns a list of all videos that have been created via the platform.
019d8488list replicas
Retrieves a full list of all trained AI video replicas available to use.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Tavus Video Replicas, then connect any of our 4,900+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,900+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Tavus. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Video production shouldn't require jumping between 5 tabs.
Today, creating a personalized video is painful. You write the script in one tool, download it to your desktop, upload it to a cloud folder, and then manually check its status on a separate platform dashboard until it's done. Then you have to find that file again later.
With this MCP server, all of that happens in chat. Your agent handles the whole chain: listing replicas via `list_replicas`, running the generation using `generate_replica_video`, and tracking its status—all without leaving your conversation window.
Tavus Video Replicas MCP Server: Run video ops from chat.
You ditch the manual process of copying IDs, checking external dashboards, and manually triggering the next step. The agent manages state for you.
The result is a fully conversational workflow. You ask it to generate something, and it confirms when `vid_789` is ready, handing you the download link—period.
What you can do with this MCP connector
This server connects your agent directly to Tavus, letting you manage and generate personalized AI video content. You're running trained virtual clones—replicas—to create high-quality talking-head videos on demand.
Managing Your Replicas.list_replicas gives you a complete rundown of every single trained video replica available to your agent. If you need specifics, get_replica_details pulls up all the data for one particular clone’s settings. You can also permanently delete unused clones using delete_replica, which cleans out that storage space.
Generating Content.
Need a new video? Just use generate_replica_video. You feed it a script and tell your agent exactly which replica to use; it handles the rest. When you’re ready, your agent can check the status of any job with get_video_details or get general details about the content using list_generated_videos. The system also lets you list every video asset that's been created on the platform via list_generated_videos.
Viewing and Cleaning Up.
To see everything you’ve built, your agent runs list_generated_videos, giving you a complete view of all generated videos along with their direct download links. If you only need to know about one specific video, use get_video_details for the granular info. When you're done with a piece or a clone, you can hit delete using delete_video to remove a finished video file, or delete_replica again if that trained replica isn't needed anymore.
This setup lets your agent manage every part of the process—from listing what clones you have (list_replicas) and checking their settings (get_replica_details), right through generating the talking-head video (generate_replica_video). It also tracks progress by providing detailed status checks on any given job, confirming when it's good to download. You can verify every piece of content with list_generated_videos, which returns a comprehensive list and associated links for all your finished work.
Cleaning up is simple: use delete_video if you want to wipe out a specific asset, or call delete_replica when a trained model is obsolete.
You don't have to juggle multiple systems to keep track of everything. Your agent keeps the content library clean by allowing you to list every existing video (list_generated_videos) and get granular details on any single piece (get_video_details). The workflow runs entirely through natural language commands, making it fast. If you change your mind about a specific replica's parameters or need to confirm its existence, get_replica_details gives you the definitive data.
This whole operation lets you treat your personalized video content like a managed asset vault. You get the list (list_replicas), check the specifics (get_replica_details), generate new stuff using those tools (generate_replica_video), track its readiness status, and then either keep it forever or delete it with delete_video or delete_replica. It's a closed loop of creation, monitoring, and cleanup.
019d8488-59bd-72ca-9d5b-f0eec0f0a536 
How Tavus Video Replicas MCP Works
- 1 Subscribe to this server and input your Tavus API Key (v2).
- 2 Instruct your agent using natural language, for example: 'List my available replicas.'
- 3 The agent executes the necessary tool call (e.g.,
list_replicas) and returns the data you need.
The bottom line is: You talk to your AI client, and it handles all the calls to Tavus for video operations.
Who Is Tavus Video Replicas MCP For?
Marketers who run large-scale campaigns. Sales professionals needing instant custom outreach videos. Customer Success managers building personalized onboarding content.
Uses the server to generate hundreds of tailored video ads quickly, managing replicas and checking generation status at scale.
Generates custom 'Hi [Name], here's a quick video on X' outreach videos for cold prospects using an AI clone of the founder.
Creates personalized training or support videos for new clients without needing to record anything themselves.
What Changes When You Connect
- Scale Personalized Content: Don't manually record outreach. Use
generate_replica_videoto create custom, personalized video campaigns for hundreds of prospects instantly. - Full Asset Lifecycle Control: Keep your workflow clean. You can use
list_generated_videos, inspect them withget_video_details, and then trash the old ones withdelete_videowhen they're done. - Instant Replica Audit: Need to know if a clone is set up right? Use
list_replicasorget_replica_detailsto check all your training assets without clicking through menus. - Workflow Automation: Your agent handles the status checks. Instead of waiting, it monitors generation tasks and alerts you when the video ID (like
vid_789) is ready for download links. - Predictable Output: The clear separation between listing (
list_replicas) and generating (generate_replica_video) means your agent always knows exactly which source clone to use.
Real-World Use Cases
The Cold Outreach Blitz
An SDR needs 50 unique videos for a cold list. Instead of recording, they tell their agent: 'Generate videos using replica 'Founder Clone' with the script about our new API.' The agent runs generate_replica_video multiple times and tracks all resulting video IDs.
Cleaning Up Old Content
A marketing manager finishes a campaign. They run list_generated_videos to see everything, find the old videos marked 'Q3 Campaign', and use delete_video on each one so they don't clutter the library.
Pre-Flight Check
Before generating anything, a user needs confirmation that their new clone is ready. They ask the agent to run list_replicas, confirm the ID, and then use get_replica_details to validate its status.
Auditing Assets
A team lead needs a full inventory of all video assets. They ask the agent to run list_generated_videos, which provides the list, and then they can use get_video_details on specific IDs for final review.
The Tradeoffs
Assuming one tool does it all
Telling the agent to 'make me a video and clean up everything.' This is too vague; it leaves status tracking or deletion ambiguous.
→
Break it down. First, list assets (list_generated_videos). Second, generate the required content using generate_replica_video. Third, once done, explicitly tell the agent to run delete_video on the specific ID.
Over-relying on details
Getting video details (get_video_details) and replica details (get_replica_details) back-to-back without a clear purpose. It creates redundant steps.
→
Use the listing tools first. If you need to verify one item, use get_video_details or get_replica_details. Otherwise, stick to the list commands (list_generated_videos or list_replicas).
Ignoring necessary cleanup
Generating videos and leaving dozens of unused replicas in the system over time. This creates technical debt.
→
Always run delete_replica on clones that are retired. It keeps your asset list clean and manageable.
When It Fits, When It Doesn't
Use this server if your core need is automated, high-volume video production using AI clones. If you're building a pipeline where content must pass through the 'script -> replica -> generated video' sequence, this is it. You should use generate_replica_video immediately after confirming availability with list_replicas. Don't use this if your goal is simple data storage or message sending; those tasks require different types of integration tools. If you only need to read the list of assets without generating anything, stick to list_generated_videos, and don't call get_video_details until you have a specific ID ready.
Common Questions About Tavus Video Replicas MCP
How do I list all my video clones using list_replicas? +
Just tell your agent to 'List my replicas.' The list_replicas tool will run and show you every trained clone ID available in the system.
What is the difference between list_generated_videos and get_video_details? +
list_generated_videos gives you a quick directory of all videos. Use get_video_details when you need deep info on one specific video, like its exact generation metadata.
Can I delete an old replica using delete_replica? +
Yes. If a clone is retired and you won't use it again, run delete_replica to permanently remove it from your asset list. This keeps things clean.
What do I provide for generate_replica_video? +
You must give the agent three things: the script content, and a specific replica ID (e.g., 'rep_123'). The tool needs these inputs to start.
How do I track if my video generation is finished? +
After running generate_replica_video, ask the agent to check the status. It manages that background task and tells you when the content moves from 'pending' to 'ready'.
What key information do I need to use any tool, like `generate_replica_video`? +
You must provide a valid Tavus API Key. The server needs this credential in your connection settings before it will execute any function calls or manage resources.
When I run `get_video_details`, what metadata fields should my agent expect to receive? +
The tool returns comprehensive asset data, including the video's current status (e.g., processing, ready), its unique ID, and a link to the final generated file.
How does my agent handle rate limits when calling tools like `list_replicas`? +
Your agent must check for HTTP 429 status codes. If it hits a limit, your client needs logic to pause and retry the request after a specified delay.
How do I create a replica? +
Replicas currently must be initiated via the Tavus Dashboard or their specific training endpoints which require a source video. This agent allows you to manage and use existing replicas.
How long does video generation take? +
Personalized video generation typically takes a few minutes depending on the length of the script. You can use the get_video_details tool to check if the status is 'completed'.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.