1
Copy the Viddo MCP URL
Copy the Viddo MCP server URL. You will need it in the next step.
https://mcp.viddo.ai/mcp
Seedance 2.0: Desde $0.345 por video
Veo3.1 Lite: Desde $0.0575 por video
Copy the Viddo MCP server URL. You will need it in the next step.
https://mcp.viddo.ai/mcpOpen the page below and click New Connector, then Custom. Name it Viddo, paste the URL, and click Add Connector.
Sign in with your Viddo account and approve the connection. Then ask Grok to generate and edit images, videos, and audio.
Verify the connection
Please call viddo_list_models and list the models available on my account.You authorize with your Viddo account in the browser. There is no key to create, copy, rotate, or paste into a config file.
A single server exposes 40+ video, image, and audio models. Your agent reads the live model list and picks a compatible one instead of you memorizing model names.
Create a shot, refine it, and try a variation without leaving the conversation or switching tools. Each result becomes the input for the next step.
Your agent can read your balance and estimate a job before creating it. Nothing runs until you approve the model, the parameters, and the credit cost.
Finished assets come back as links your agent can reference, download, or drop straight into the project you are already in.
Submit several generation tasks at once, get a separate status for each, and avoid rewriting the same prompt for every variation.
Give your agent the full Viddo catalog instead of a single endpoint. The list below is the current set of models available over MCP.
Any client that supports a remote MCP server over Streamable HTTP. That includes ChatGPT, Claude, Grok, Microsoft Copilot Studio, Cursor, Claude Code, VS Code, Gemini, Codex, Cline, Zed, OpenCode, Roo Code, and OpenClaw.
No. You authorize with your Viddo account in the browser. There is no key to create, copy, rotate, or paste into a config file.
Jobs use your Viddo credits. Your agent can estimate the credit cost first and wait for your confirmation before creating the job.
Yes. The agent reads the live model list and can pick a compatible model instead of you memorizing names.
Yes, on models that support them. Your agent can pass reference assets through the Viddo MCP tools.
Yes. Text to speech, voice cloning, and music generation are available over the same connection.
Finished assets come back as links your agent can reference, download, or drop straight into the project you are already in.
No. Failed jobs are not billed twice. You are charged for successful generation on your Viddo credits.
Viddo MCP uses your Viddo account and credits. Your ChatGPT, Claude, or Cursor subscription is only needed to use that client.
Bring the full Viddo catalog into the assistant you already use. Sign in once with your Viddo account, and start creating on your next message.
Viddo AI es una plataforma avanzada de generación de imágenes y videos con IA todo en uno que le permite crear rápida y fácilmente videos e imágenes impresionantes a partir de diversas entradas. Estos modelos de IA funcionan con Google, OpenAI, Grok AI, ByteDance, Alibaba, Kling, Runway, Vidu, Minimax, Elevenlabs, Midjourney, etc.