AITuber MCP Server
OfficialThis server lets AI assistants create, manage, and publish AI-powered videos from natural language prompts. Capabilities include:
Generating short-form (Shorts, Reels) or long-form videos from a topic or script, with AI narration, visuals, and synced captions.
Accessing 1,300+ AI voices (filter by gender, accent, age, language) and 27+ visual styles (photorealistic, anime, cinematic, 3D Pixar, watercolor, etc.).
Using templates: skeleton X-ray, character-driven stories, avatar talking-head.
Choosing media: AI images, AI video clips, or real stock footage.
Creating music videos: generate songs from a prompt or upload tracks, with AI visuals and synced lyrics.
Uploading assets, saving reusable elements (@handles), and managing UGC reaction clips.
Generating content ideas and narration scripts.
Managing videos (list, view, delete, poll status, export to MP4).
Making standalone AI video clips from prompts or images.
Publishing to YouTube, TikTok, Instagram, Facebook, Threads, and X, with scheduling.
Checking subscription, credits, billing, and connected social channels.
Browsing available voices, avatars, styles, and clip models.
Using two tools:
search_apito find endpoints in natural language, andexecute_apito call any endpoint with auto authentication.
Create and publish AI-generated videos directly to Instagram Reels, with narration, captions, and visual styles.
Generate and publish AI-powered videos to TikTok, supporting short-form content with AI voices and visuals.
Produce and publish AI-narrated videos to YouTube, including long-form content and shorts, with direct channel integration.
Create AI-generated short-form vertical videos for YouTube Shorts, with automated narration, captions, and visual generation.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AITuber MCP ServerCreate a 60-second video on Mars exploration"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AITuber MCP Server
Create AI-powered videos from your AI assistant. Generate videos with AI narration, visuals, and synced captions for YouTube Shorts, TikTok, Instagram Reels, and long-form content. Supports AI-generated images, video clips, stock footage, and viral templates like skeleton and character styles. AITuber handles script writing, voice synthesis, visual generation, and video rendering.
One server, one URL:
https://mcp.aituber.appAITuber | Setup Guide | API Documentation
Set up your client
claude.ai and Claude Desktop
Open Settings, go to Connectors, click "Add custom connector", and paste https://mcp.aituber.app. A browser window opens to sign in with your AITuber account. Done.
Claude Code
claude mcp add --transport http aituber https://mcp.aituber.appYour browser opens once to sign in and approve access.
ChatGPT
Open Settings, go to Connectors, then Advanced, and turn on Developer mode (required for custom connectors). Add a new connector with the URL https://mcp.aituber.app and sign in with your AITuber account.
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"aituber": {
"url": "https://mcp.aituber.app"
}
}
}Codex
Add to ~/.codex/config.toml:
[mcp_servers.aituber]
url = "https://mcp.aituber.app"OpenClaw and other MCP clients
Add a remote MCP server with the URL https://mcp.aituber.app. If your client supports OAuth, sign in when prompted. If it asks for credentials instead, use an API key (next section).
Related MCP server: arcframe-mcp
Two ways to sign in
1. Your AITuber login (default). Apps like Claude, ChatGPT, and Cursor open a browser window where you sign in and approve access. No key to copy, nothing to store.
2. An API key (servers, CI, automation). Where a browser sign-in is not practical (a VPS, CI pipeline, n8n, cron), create a key at app.aituber.app/dashboard/api-keys (starts with ak_) and send it as a bearer token to the same URL:
claude mcp add --transport http aituber https://mcp.aituber.app \
--header "Authorization: Bearer ak_your_key_here"{
"mcpServers": {
"aituber": {
"url": "https://mcp.aituber.app",
"headers": {
"Authorization": "Bearer ak_your_key_here"
}
}
}
}API keys are long-lived and revocable from the dashboard, so they fit unattended automation better than OAuth tokens.
What you can do
Generate videos from a prompt or script - describe a topic and get a fully produced video, or provide exact narration text for precise control
Short-form and long-form - create 15-second Shorts or 20-minute videos
1,300+ AI voices - filter by gender, accent, age, or language
27+ visual styles - photorealistic, anime, cinematic, 3D Pixar, watercolor, comic book, and more
Video templates - skeleton X-ray style, character-driven stories
Multiple media types - AI-generated images, AI video clips, or real stock footage
Music videos - generate a song from a prompt (or upload your own track) and turn it into a music video with AI visuals and synced lyric captions
Six publishing platforms - publish to YouTube, TikTok, Instagram, Facebook, Threads, and X
Export to MP4 - render and download the final video
Check credits and plan - monitor usage before generating
Start creating
Ask your AI assistant:
"Create a 60-second video about 5 mind-blowing facts about the ocean"
"List available British female voices for narration"
"Check how many credits I have left"
"Export my latest video to MP4 and give me the download link"
"List my connected channels and publish my finished video to Threads and X"
How it works
The server provides two tools:
search_api
Finds the right AITuber API endpoint for your task. Describe what you want in natural language.
search_api("create a video about cats")
-> Returns: POST /videos/generate with all parameters and examplesexecute_api
Calls the AITuber API. Use after search_api to know which endpoint and parameters to use.
execute_api(method: "POST", path: "/videos/generate", body: {
"script": "5 amazing facts about the deep ocean",
"inputType": "idea",
"expectedDurationSeconds": 60
})
-> Returns: { videoId: "abc-123", status: "pending" }Example workflows
Generate and download MP4
Search - find the right endpoint for creating a video
Generate - create the video with your script and settings
Poll - check video status until generation completes
Export - render the completed video to MP4
Download - get the MP4 download URL
Generate and publish
Generate - create the video with your script and settings
Poll - wait until the video status is
completedList channels - call
GET /channelsto find connected channel IDsPublish - call
POST /publicationswith thevideoIdand per-channel settingsPoll publication - call
GET /publications/{publicationId}until it reachespublished,scheduled, orfailed
Publishing requires channels to already be connected through the AITuber dashboard and an active paid plan with the Publish feature. If the video is not exported yet, the API starts the export automatically.
Generate a music video
Make a song - call
POST /musicwith a prompt (or upload a track withPOST /uploadspurposemusic)Poll the song - call
GET /music/{id}until status iscompletedBuild the video - call
POST /music-videoswith themusicId(ormusicAssetId) and avisualMode(ai-images,ai-video, orcover-image)Poll the video - call
GET /videos/{id}until status iscompleted, then export or publish it
API endpoints
Endpoint | Description |
| Browse 1,300+ AI voices with filters (public, no auth required) |
| List voices you cloned in the dashboard |
| List avatars for talking-head videos |
| List saved people, products, and places (with @handles) |
| Save an element from a photo URL or uploaded asset |
| Upload media (from a URL or a direct PUT) |
| List UGC reaction clips (library + your own) |
| Generate a reaction clip from your character |
| Get a reaction clip status |
| Build a finished UGC hook video |
| Generate an original song from a prompt |
| List your generated and uploaded tracks |
| Get a song's status and audio URL |
| Turn a song into a music video with AI visuals |
| Get video topic ideas for a niche |
| Write a narration script from a topic |
| List image styles for video generation |
| List caption styles for video generation |
| Create a video from a script or idea |
| List all your videos |
| Get video details and generation status |
| Delete a video |
| List AI models for standalone clips with capabilities and costs |
| Generate a standalone AI video clip from a prompt or image |
| List your clips |
| Get clip status and download URL |
| Check your plan, credits, and billing info |
| Start rendering a video to MP4 |
| Get a temporary download URL for the MP4 |
| List connected YouTube, TikTok, Instagram, Facebook, Threads, and X channels |
| Publish a completed video to one or more connected channels |
| Check publication status after publishing |
| Cancel a scheduled publication before it goes live |
Supported video types
Type | Description | How to create |
Faceless narration (images) | AI images with Ken Burns animation, narration, and captions | Default. Just send a script or idea. |
Faceless narration (video clips) | AI-generated video clips instead of images | Set |
Stock footage | Real stock footage matched to narration | Set |
Skeleton template | Viral "what happens if..." X-ray style | Set |
Character template | Character-driven story format | Set |
Avatar (talking head) | An avatar speaks your script to the camera | Set |
Under the hood
The server is a stateless Cloudflare Worker (src/remote.ts, source in this repo). It verifies your AITuber sign-in or API key, exposes the search_api and execute_api tools, and forwards each call to the AITuber API with your own credential. Nothing is stored and there are no server-side sessions. PostHog MCP Analytics records tool names, client details, timing, and success or failure. Tool arguments and responses are removed before analytics events are sent. The endpoint catalog is generated from the API's OpenAPI definition, so the tools always match the live API. Dev and deploy notes: CONTRIBUTING.md.
Links
AITuber - AI video creation tool
Setup Guide - Connect from any client
API Documentation - Interactive API reference
Dashboard - Manage videos and billing
API Keys - Create and manage your API keys
License
MIT
Available Tools
2 toolsexecute_apiA
Execute a request against the AITuber API. Use search_api first to find the right endpoint and parameters. Handles authentication automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | Request body (for POST/PUT), e.g. { "script": "...", "mediaType": "images" } | |
| path | Yes | API endpoint path, e.g. /videos, /videos/generate, /voices, /subscription | |
| query | No | Query parameters as key-value pairs, e.g. { "limit": "10", "gender": "female" } | |
| method | Yes | HTTP method | |
| pathParams | No | Path parameter substitutions, e.g. { "id": "abc-123" } for /videos/{id} |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It mentions automatic authentication but does not disclose potential destructive behavior (e.g., creating/modifying resources) or rate limits. Minimal behavioral context beyond the basic operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with the core purpose, followed by usage guidance and a notable behavior (auth handling). No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks return value information (no output schema and no description of what the response looks like). Given 5 parameters with nested objects, a usage example would improve completeness. Does not explain how parameter interactions work (e.g., when to use query vs pathParams).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds no additional parameter meaning beyond the schema's own descriptions. The only extra info is about authentication, which is not parameter-specific.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Explicitly states it executes requests against the AITuber API, with a clear verb (execute) and resource (AITuber API). It also distinguishes from sibling search_api by advising to use search_api first.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance: use search_api first to find endpoint and parameters. Also mentions automatic authentication handling, helping the agent understand prerequisites and workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_apiA
Search the AITuber API to find endpoints for creating AI videos, checking credits, exporting to MP4, publishing to YouTube/TikTok/Instagram, and more. Returns matching endpoints with parameters and examples. Use this before execute_api to find the right endpoint.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What you want to do, e.g. "create a video", "list voices", "check credits", "download mp4", "publish to tiktok" |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
As a search tool, it is implicitly read-only. Description mentions it returns endpoints with parameters and examples, which is sufficient for a non-destructive operation. No annotations provided, but description does not hide any behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with core purpose, no irrelevant details. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description explains what is returned (matching endpoints with parameters and examples). For a simple search with one parameter, this is adequately complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and already includes examples in the parameter description. The tool description does not add deeper meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches the AITuber API to find endpoints for various tasks, distinguishing it from the sibling tool execute_api by explicitly saying to use it before execute_api.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises to use this tool before execute_api, providing clear when-to-use and alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
2 tool updates
v1.12.0- First observed
execute_api - First observed
search_api
TDQS
The two tools have clearly distinct purposes: search_api discovers endpoints and parameters, while execute_api performs the actual API call. There is no overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern (search_api, execute_api) using snake_case, making the naming predictable.
Two tools is minimal but suitable for the server's designed workflow of discovery followed by execution. While slightly thin, each tool serves a necessary and distinct role without redundancy.
The combination of search and execute covers the full lifecycle of using the AITuber API: finding the right endpoint and then executing it. Authentication and parameter handling are included, leaving no obvious gaps.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
AI video producer: directs your idea or script into a finished, fact-checked video. MCP-native.
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
Generate AI images and videos from any compatible MCP client.
Remote MCP for AI video, image, music and speech generation.
Related MCP Servers
AlicenseNot gradedqualityFmaintenanceEnables video generation from text, images, and more through MCP-compatible apps like Claude and Cursor.52MIT
arcframe-mcpofficial
AlicenseNot gradedqualityCmaintenanceGenerate videos, images, audio, and 3D models from any MCP-compatible AI agent — Claude, Cursor, ChatGPT, and more.MIT- FlicenseNot gradedqualityBmaintenanceAn MCP server that enables AI assistants to automatically generate vertical 'brainrot' style videos with text-to-speech voiceovers, synchronized subtitles, and custom SVG overlays.-
- AlicenseNot gradedqualityCmaintenanceTurns text scripts into complete videos with stock footage, AI narration, and subtitles via MCP tools for AI assistants.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aituberapp/ai-video-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server