Claude Code + Veo MCP: Generate HD AI Videos with Google Veo from the Terminal
📘 Complete Guide: Use all 11 AceData Cloud MCPs in Claude Code →
Veo is an AI video generation model launched by Google, natively supporting 1080p with fine image quality and capable of directly generating accompanying audio. If you are a developer, Claude Code + Veo MCP is the most convenient combination—generate videos using natural language directly in the terminal, no need to switch windows or learn video editing software.
¶ Obtain API Token
Before using the Veo MCP Server, you need an AceData Cloud API Token:
- Open AceData Cloud Platform, which supports login via GitHub, Google, WeChat, email, or phone number. Register to get free credits.
- After logging in, you can see the API Token on the homepage. Click to copy it.
- When credits run out, go to Console → Recharge to top up, supporting Alipay, WeChat, and Stripe.

One Token grants access to all 11 MCP Servers, no need to apply separately for each service.
💡 Using claude.ai web or Claude Desktop? They support OAuth one-click authorization without manually entering the Token. See Claude + Veo MCP Illustrated Tutorial for details.
¶ Configure Claude Code
Run the following command in the terminal, replacing 你的Token with the API Token copied in the previous step:
claude mcp add veo --transport http https://veo.mcp.acedata.cloud/mcp \
-H "Authorization: Bearer 你的Token"
⚠️
-Hmust be uppercase. Lowercase-his--help, not a header parameter.
Without -s, the default scope is local, which only applies to the directory where the command is run. It is recommended to explicitly specify the scope:
| Scope | Command Parameter | Config File | Scope of Effect |
|---|---|---|---|
local (default) |
no -s or -s local |
~/.claude.json |
Only the project directory where the command runs |
user |
-s user |
~/.claude.json |
Global effect, available in all projects |
project |
-s project |
.mcp.json in project root |
Current project, can be committed to git and shared with team |
💡 To share the same configuration with your team, add
-s project: the config will be written to the project root.mcp.jsonand can be shared via git clone. Do not commit real Tokens to public repositories; use${ENV_VAR}placeholders with environment variables instead.
Verify the setup by running claude mcp list, you should see veo showing ✓ Connected.
¶ Practical Examples
After configuration, return to the Claude Code session and call Veo using natural language directly:
Generate a demo video for a project
I am developing a weather app, help me generate a demo video: the phone screen shows weather information, the background transitions from sunny to rainy
Generate an animation for documentation
Generate an animation for the README document: data flows from the input box on the left to the result panel on the right, passing through three processing nodes in the middle
Generate video with audio
veo_generate_video_with_audio natively outputs accompanying audio:
Generate a short video with audio: code is typed automatically on a black background, keyboard clicking sounds, finally compilation succeeds, a green ✓ appears
¶ Tool List
| Tool | Description |
|---|---|
| veo_generate_video | Generate video from text or images |
| veo_generate_video_with_audio | Generate video with audio |
