generate_video
Create a video task; discover options with list_video_models and get_video_model.
Generate AI video, images, music, and audio from Claude, ChatGPT (Codex), Cursor, or any agent that speaks MCP.
Connect
Create an API key, add this server configuration, then ask your agent to create a video.
In claude.ai or the Claude desktop app, go to Settings > Connectors > Add custom connector, name it Vidrush, paste this URL, then click Connect and sign in with your Vidrush account. No API key needed.
https://vidrush-ai.com/api/mcpAgents that can edit their own MCP configuration can connect themselves. Replace YOUR_API_KEY, then paste:
Add the Vidrush MCP server to this client: streamable HTTP transport, URL https://vidrush-ai.com/api/mcp, HTTP header "Authorization: Bearer YOUR_API_KEY". Then call the list_video_models tool to verify the connection.
Capabilities
The Vidrush MCP server generates video, image, music, and audio. Generation consumes credits.
Create a video task; discover options with list_video_models and get_video_model.
Text-to-image or image-to-image; browse models with list_image_models.
Create an original music track from a prompt; see list_music_models.
Convert text to speech with a chosen voice from list_voices.
Generate a sound effect from a text prompt.
Get a task's current status and completed output URLs.
Wait up to 50 seconds, then return the latest status. Call it repeatedly for longer generations.
Check the remaining credits in your authenticated account.
Example
You
Make an 8s 720p video of a paper kite crossing a bright summer sky.
Your agent calls generate_video
{ "model": "sora-2", "prompt": "A paper kite crossing a bright summer sky", "duration": "8s", "resolution": "720p" }
Then get_task returns
{ "task_id": "task_123", "status": "success", "video_urls": ["https://.../video.mp4"] }
FAQ
Create an API key and connect the Vidrush MCP server in a few minutes.