Skip to main content
Glama

gwanggo-mcp

让您的 AI 代理获得生成图像和视频的能力。

面向 Gwanggo API 的 MCP 服务器 + CLI — 一个密钥即可使用 Seedream、Sora、Veo、Kling、GPT Image 等 30 多个模型。

npm License: MIT MCP

适用于 Claude Code · Claude Desktop · Cursor · Codex — 任何支持 MCP 的工具。


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

设置(2 分钟)

1. 连接您的账户(打开浏览器授权 — 无需粘贴密码):

npx gwanggo-mcp login
# or, after install:
gwanggo auth login

新账户可获得免费额度:在 gwanggo.ai 注册。您也可以跳过 login,直接设置 GWANGGO_API_KEY(在 Dashboard → API keys 创建)。

2. 添加到您的代理:

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"]

要显式传入密钥而不是使用 login,请添加 "env": { "GWANGGO_API_KEY": "gwk_..." }。

Related MCP server: Corent MCP Server

工具

Tool

功能

list_models

35+ 个图像/视频模型,含积分费用和每个模型的选项

generate_image

文本→图像 / 图像编辑。等待完成,返回 URL

generate_video

文本→视频 / 图像→视频(Seedance 2.0、Kling 3.0、Veo 3.1、Sora 2 …)

get_task

按 id 检查之前的生成任务

get_credits

剩余积分余额

失败的生成任务会在服务端自动退款。

CLI 用法

同一个二进制文件兼作 CLI:

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

gwanggo 命令复用 gwanggo auth login 保存的账户;无需 API 密钥 环境变量。GWANGGO_API_KEY 仍可用于 CI 和其他非交互式环境。

工作原理

基于公共 Gwanggo /v1 REST API 的轻量客户端 — 与驱动开源 Gwanggo Studio 的 API 相同。您的密钥存储在 ~/.config/gwanggo/config.json(0600),仅以 Bearer token 形式发送。浏览器登录的密钥优先于 GWANGGO_API_KEY,因此过期的环境密钥无法覆盖新批准的登录。在 CI 中,由于不存在登录文件,将使用 GWANGGO_API_KEY。

许可证

MIT

Available Tools

5 tools
generate_imageA

Generate an image with a Gwanggo model. Spends credits. Waits for completion and returns the image URL. Use list_models first to choose a model slug and see its options.

Inputs: model (required), prompt (required), quality, image_url, +1 more.

generate_videoA

Generate a video with a Gwanggo model. Spends credits (often per-second — check list_models). Waits up to 10 minutes and returns the video URL.

Inputs: model (required), prompt (required), duration, image_url, +3 more.

get_creditsA

Get the connected Gwanggo account email and remaining credit balance.

Inputs: no named parameters.

get_taskA

Check the status/result of a previous generation by its id.

Inputs: id (required).

list_modelsA

List available AI image/video generation models with credit costs and per-model options (aspect ratios, resolutions, durations). Call this first to pick a model slug.

Inputs: type.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool serves a distinct function: generating images, generating videos, checking credits, checking task status, and listing models. No overlaps or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (generate_image, generate_video, get_credits, get_task, list_models), making predictions easy.

    Tool Count5/5

    With 5 tools, the set covers the core workflow for an AI media generation service without being too sparse or excessive.

    Completeness4/5

    The surface covers model discovery, generation for both image and video, credit tracking, and task status. Missing a cancel/delete tool is a minor gap but not critical.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI image and video generation using Google Nano Banana and Veo 3.1 via a LiteLLM gateway, providing tools for synchronous image generation and asynchronous video generation with polling, returning public URLs.
      4
      MIT
    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Gives AI assistants the ability to generate and iteratively refine images and videos with Google AI Studio models, including image creation/editing, Veo and Omni video generation, and async job tracking. Also lets them analyze existing media and list the models available with their API key.
      1
      ISC