VideoGen MCP

by @davidgrossman

MCP MCP VERIFIED Verified 4 days ago paid

Create editable videos and AI media from your assistant with the official VideoGen MCP server.

70 agent lookups
· last 90 days

VideoGen MCP is the official Model Context Protocol server for the VideoGen developer API. It gives compatible assistants 50 tools to create editable videos from scripts, voiceovers, slideshows and storyboards; generate images, video clips, voiceovers, music and motion graphics; manage files and projects; and export videos. Use it with Claude, ChatGPT, Cursor, VS Code, Codex or another compatible MCP client. The open-source TypeScript server runs locally with npx -y @videogen/mcp and a VIDEOGEN_API_KEY, or as hosted Streamable HTTP at https://mcp.videogen.io/mcp using OAuth or a VideoGen API key. Media generation requires a VideoGen account and paid generation credits. Setup: https://videogen.io/videogen-mcp . Developer documentation: https://docs.videogen.io/libraries/mcp . Full tool input/output schemas are published in the official GitHub repository.

Problem it solves

Lets assistants create, edit and export videos through one documented API, reducing the manual work of moving between media generation and video workflow tools.

How it's different

Produces editable VideoGen projects alongside exports, with four video workflows, 50 documented tools, and both local API-key and hosted OAuth connection options.

Features

50 callable tools with public input/output schemas
Script, voiceover, slideshow and storyboard video workflows
Editable projects and video export
Image, video, voiceover and music generation
Hosted Streamable HTTP with OAuth or API-key authentication
Local stdio through npx -y @videogen/mcp
MIT-licensed TypeScript source

From the maker

Official VideoGen server, submitted by the VideoGen team. The supplied /mcp/chatgpt endpoint permits anonymous initialize and tools/list discovery; authenticated tool calls require OAuth or a VideoGen API key, and generation requires credits. The canonical hosted endpoint is https://mcp.videogen.io/mcp. Setup and website: https://videogen.io/videogen-mcp . Full input/output schemas: https://github.com/video-gen/videogen-mcp/blob/main/tool-schemas.json . Contact: info@videogen.io.

Gallery

Tools this endpoint exposes

Read directly from the endpoint on 6 Oct 2026. Not supplied by the maker.

get_getting_started_guidance
How to authenticate, verify with get_me, introduce VideoGen with workflow example prompts, choose workflows vs media tools, and follow VideoGen id conventions. Call when connecting, onboarding, the us
get_async_tasks_guidance
How to handle async workflows, tool executions, and exports: statuses, hosted vs local wait caps, polling with get_* tools, and when webhooks apply outside MCP. Call before polling or when a start too
get_workflows_guidance
Canonical run → remix → export flow and when to use each workflow tool. Prefer script_to_video for longer narrated / informational videos; keep storyboard_to_video to ≤3 scenes unless the user asks fo
get_tools_vs_workflows_guidance
When to use standalone media tools (automatic model routing for a single asset) versus workflows (full editable professional video). Call when choosing between generate_* tools and workflow tools. Equ
script_to_video
Preferred for narrated / informational / explainer videos from text, especially ~1 minute or longer. Turn a verbatim narration script into an editable video with AI-generated visuals and captions. Pre
voiceover_to_video
Build an editable video with AI-generated visuals from an uploaded voiceover audio file.
slideshow_to_video
Build an editable narrated video from an uploaded PDF or slideshow file. Upload the file first with upload_file, then pass its fileId. For avatar narration, pass actorEntityId and optionally set avata
storyboard_to_video
Build an editable video from an ordered storyboard (frame-by-frame shot list). Every scene needs a visual prompt and may include spoken words. Much more credit-heavy than script_to_video: use at most