OpenCode Integration with Veo MCP

📘 Overview：OpenCode MCP Overview →

The Google Veo series is currently the most distinctive video generation model in "native audio + high resolution" — veo3 / veo31 can generate synchronized ambient sounds and music while creating images, while the veo2-fast series is the most practical for "image-to-video" and "frame interpolation." After connecting to the Veo MCP Server in OpenCode, you can produce videos with sound in one go, eliminating the need for post-production on tracks.

Veo MCP is suitable for creating product introduction videos that require native audio, film storyboard samples, and scenarios like "transition animations between two design drafts."

Obtain API Token

Before using the Veo MCP Server, you need to prepare an Ace Data Cloud API Token. OpenCode and Claude Code share a set of Tokens, and the acquisition process is the same:

  1. Open the Ace Data Cloud Console - Application List to obtain your API Token for backup.
  2. If you are not logged in or registered, you will be automatically redirected to the login page; after logging in or registering, you will be automatically returned to the current page.
  3. The first application will come with a free quota, allowing you to experience the Veo MCP service for free.

One Token can be used for all 11 MCP Servers provided by AceData Cloud, without needing to apply separately for Veo. The documentation and screenshots suggest displaying only in a de-sensitized form, such as 3b78cc40dd3b43db806a4300...., and do not paste the complete Token into public repositories, issues, screenshots, or chat records.

Want to use Claude Desktop / Claude.ai web version for direct OAuth one-click authorization? Please see the Claude.ai / Desktop tutorial for Veo MCP.

Configure OpenCode

OpenCode describes all MCP Servers in a single opencode.json file, which can be placed in two locations; choose one according to the "scope of application" below. The field structure in both locations is exactly the same, with the only difference being priority.

It is strongly recommended to first write the Token to an environment variable:

export ACEDATACLOUD_API_KEY="replace with your real Token"

Then reference it in opencode.json using the {env:ACEDATACLOUD_API_KEY} placeholder to avoid writing the real Token into the file.

Global: Shared by all projects

File location: ~/.config/opencode/opencode.json, suitable for "my own machine, configured once, usable by all projects."

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "veo": {
      "type": "remote",
      "url": "https://veo.mcp.acedata.cloud/mcp",
      "enabled": true,
      "oauth": false,
      "headers": { "Authorization": "Bearer {env:ACEDATACLOUD_API_KEY}" }
    }
  }
}

⚠️ "oauth": false cannot be omitted. AceData's MCP Server uses Bearer Token authentication and does not go through the OAuth process; OpenCode will automatically redirect 401 as an OAuth challenge by default, causing opencode mcp list to show SSE error: Non-200 status code (401). Explicitly declaring "oauth": false allows OpenCode to call directly with Authorization: Bearer ..., and opencode mcp debug veo will also echo OAuth explicitly disabled, indicating it is effective.

Project-level: Effective only for the current project

File location: opencode.json in the current project root directory, which will override the global configuration. Suitable for team sharing, single repository customization, or temporarily enabling a specific MCP in a certain project.

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "veo": {
      "type": "remote",
      "url": "https://veo.mcp.acedata.cloud/mcp",
      "enabled": true,
      "oauth": false,
      "headers": { "Authorization": "Bearer {env:ACEDATACLOUD_API_KEY}" }
    }
  }
}

If the project-level opencode.json will be committed to Git, please ensure to use the {env:ACEDATACLOUD_API_KEY} placeholder instead of the real Token to avoid leakage.

💡 If the .env in Shell is not explicitly exported, you need to use set -a && source .env && set +a to pass the variables to the OpenCode process; otherwise, opencode debug config will show "Authorization": "Bearer " (the placeholder is not resolved).

Actual Running Results

Below is the de-sensitized output after actual execution in an isolated temporary directory in OpenCode 1.15.13. The command uses the real AceData Cloud Token, and the Token in the output has been replaced with 357265014ad145fc8ab2...., and the temporary configuration has been deleted.

$ opencode --version
1.15.13

$ opencode mcp list

┌  MCP Servers
│
●  ✓ veo connected
│      https://veo.mcp.acedata.cloud/mcp
│
└  1 server(s)

Seeing ✓ veo connected indicates that Veo MCP has been successfully integrated. If it shows ✗ or unauthorized, please check whether ACEDATACLOUD_API_KEY is set, whether the Token is copied completely, and whether the Authorization prefix is Bearer (pay attention to case and spaces).

To debug the connection details of a specific MCP:

opencode mcp debug veo

After a successful handshake, OpenCode's INFO log will output service=mcp key=veo transport=StreamableHTTP connected and service=mcp key=veo toolCount=12 (tested with 12 tools), indicating that Veo MCP is ready to be called by the model.

🤖 Model selection practical advice: To truly allow the model to actively call Veo MCP in OpenCode, please prioritize using OpenAI series models (such as acedatacloud/gpt-5-mini, acedatacloud/gpt-5). When the Claude series models on AceData are exposed through the OpenAI compatible interface, tool calls often return Improperly formed request (tested: acedatacloud/claude-haiku-4-5-20251001, acedatacloud/claude-sonnet-4-6 reported this error when mounting multiple MCPs). Claude models can be used normally when only doing dialogue without calling tools.

Typical Scenarios

After configuration is complete, you can directly call using natural language in the OpenCode session without switching to /mcp:

Image-to-video + Frame interpolation + 1080p

Use these two design drafts to generate a transition animation with frame interpolation, then export it as 1080p

Video with native audio

Generate a video with veo3: a convenience store on a rainy night, the sound of rain on the glass door, the doorbell ringing, and soft background music

Video extension

Extend this video by 8 seconds, maintaining the same atmosphere

Tool List

The table below lists the main tools (Veo MCP Server has exposed a total of 12 tools, which can be obtained through curl -X POST https://veo.mcp.acedata.cloud/mcp -H 'Authorization: Bearer <token>' -H 'Accept: application/json' -H 'Content-Type: application/json' --data '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' for a complete list):

Tool Description
veo_text_to_video Text to video generation
veo_image_to_video Image to video generation (supports first/last frame)
veo_extend_video Video extension
veo_get_1080p Get 1080p HD version