gwanggo-mcp

Give your AI agent the power to generate images & video.

MCP server + CLI for the Gwanggo API — Seedream, Sora, Veo, Kling, GPT Image and 30+ more models behind one key.

Works with Claude Code · Claude Desktop · Cursor · Codex — anything that speaks MCP.

You: "우리 신제품 세럼 광고 이미지 만들어줘, 화장품 무드로"
Agent: [calls generate_image with seedream-5] → https://…/result.png

Setup (2 minutes)

1. Connect your account (opens a browser approval — no password pasting):

npx gwanggo-mcp login

New accounts get free credits: sign up at gwanggo.jocoding.io. You can also skip login and set GWANGGO_API_KEY (create one at Dashboard → API keys).

2. Add to your agent:

Claude Code

claude mcp add gwanggo -- npx -y gwanggo-mcp

Claude Desktop / Cursor (claude_desktop_config.json / .cursor/mcp.json)

{
  "mcpServers": {
    "gwanggo": {
      "command": "npx",
      "args": ["-y", "gwanggo-mcp"]
    }
  }
}

Codex CLI (~/.codex/config.toml)

[mcp_servers.gwanggo]
command = "npx"
args = ["-y", "gwanggo-mcp"]

To pass the key explicitly instead of login, add "env": { "GWANGGO_API_KEY": "gwk_..." }.

Related MCP server: MCP Veo 3 Video Generation Server

Tools

Failed generations are auto-refunded server-side.

CLI usage

The same binary doubles as a CLI:

npx gwanggo-mcp models
npx gwanggo-mcp generate image "neon alley cat, cinematic" --model gpt-image-2 --quality high
npx gwanggo-mcp generate video "waves crashing at dawn" --model seedance-2.0 --resolution 720p --duration 5
npx gwanggo-mcp me          # credits
npx gwanggo-mcp task <id>   # check status

How it works

Thin client over the public Gwanggo /v1 REST API — the same API that powers the open-source Gwanggo Studio. Your key is stored at ~/.config/gwanggo/config.json (0600) and sent only as a Bearer token.

License

MIT