F
licenseNot graded
qualityD
maintenanceProvides tools to interact with RunwayML and Luma AI APIs for video and image generation, including text-to-video, image-to-video, prompt enhancement, and management of generations.
17
-
gwanggo-mcp
by bill-950207
gwanggo-mcp
AIエージェントに画像・動画生成の力を。
Gwanggo API 用のMCPサーバー + CLI — Seedream、Sora、Veo、Kling、GPT Image など30以上のモデルを1つのキーで。
Claude Code · Claude Desktop · Cursor · Codex など、MCPに対応するあらゆるツールで動作します。
You: "우리 신제품 세럼 광고 이미지 만들어줘, 화장품 무드로"
Agent: [calls generate_image with seedream-5] → https://…/result.pngセットアップ（2分）
1. アカウントを接続（ブラウザでの承認が開きます — パスワードの貼り付けは不要）：
npx gwanggo-mcp login
# or, after install:
gwanggo auth login新規アカウントには無料クレジットが付与されます：gwanggo.ai でサインアップしてください。
loginをスキップしてGWANGGO_API_KEYを設定することもできます（ダッシュボード → APIキー で作成）。
2. エージェントに追加：
Claude Code
claude mcp add gwanggo -- npx -y gwanggo-mcpClaude 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"]login の代わりにキーを明示的に渡すには、"env": { "GWANGGO_API_KEY": "gwk_..." } を追加します。
Related MCP server: vicsee-mcp-server
ツール
ツール | 説明 |
| クレジットコストとモデル別オプションを含む35以上の画像・動画モデル |
| テキスト→画像 / 画像編集。完了を待ってURLを返します |
| テキスト→動画 / 画像→動画（Seedance 2.0、Kling 3.0、Veo 3.1、Sora 2 …） |
| 以前の生成をIDで確認 |
| 残りのクレジット残高 |
失敗した生成はサーバー側で自動返金されます。
CLIの使い方
同じバイナリがCLIとしても機能します：
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 statusgwanggo コマンドは gwanggo auth login で保存されたアカウントを再利用します。APIキーの環境変数は不要です。GWANGGO_API_KEY はCIやその他の非対話環境でも引き続き使用できます。
仕組み
公開されている Gwanggo /v1 REST API のシンクライアントです — オープンソースの Gwanggo Studio を支えるのと同じAPIです。キーは ~/.config/gwanggo/config.json（0600）に保存され、Bearerトークンとしてのみ送信されます。ブラウザログインのキーは GWANGGO_API_KEY より優先されるため、古い環境キーが新しく承認されたログインを上書きすることはありません。ログインファイルが存在しないCIでは、GWANGGO_API_KEY が使用されます。
ライセンス
Available Tools
5 toolsgenerate_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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model slug, e.g. "seedream-5", "gpt-image-2" | |
| prompt | Yes | What to generate | |
| quality | No | Model-dependent quality tier, e.g. "basic" | "high" | |
| image_url | No | Reference image URL for edit/i2i models | |
| aspect_ratio | No | e.g. "1:1", "16:9", "9:16" (model-dependent) |
TDQS
A4.3/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that it spends credits, waits for completion, and returns an image URL. No annotations provided, but description effectively communicates the synchronous mutation nature and cost.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise, front-loaded sentences with no waste. First sentence states primary action, second adds behavioral notes, third provides prerequisite guidance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Explains overall behavior and prerequisite, but lacks discussion of error handling, timeouts, or output details beyond URL. With no output schema and moderate complexity, some gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all 5 parameters. Description adds value by linking model parameter to list_models and noting model-dependent options for quality and aspect_ratio.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it generates an image using a Gwanggo model, spends credits, waits for completion, and returns the URL. Distinguishes from siblings like generate_video and list_models.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use list_models first to choose a model slug and see options, providing clear prerequisite context. No explicit when-not or alternatives, but guidance is actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model slug, e.g. "seedance-2.0", "kling-3", "veo-3.1" | |
| prompt | Yes | Scene/motion description | |
| duration | No | Seconds (model-dependent, e.g. 5 or 10) | |
| image_url | No | Reference image URL for image-to-video | |
| resolution | No | e.g. "480p", "720p", "1080p" (model-dependent) | |
| aspect_ratio | No | e.g. "16:9", "9:16" (model-dependent) | |
| generate_audio | No | Generate audio track (model-dependent) |
TDQS
A4/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description effectively discloses key behaviors: credit cost (per-second, check list_models), wait time up to 10 minutes, and return of a video URL. This goes beyond a simple definition.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. The first sentence states the purpose, the second adds critical behavioral details. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 7 parameters and no output schema, the description covers core behaviors (cost, wait, return value). Minor gaps: no mention of error handling or async fallback, but overall sufficient for a generation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions. The description adds no extra meaning to parameters, so baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('generate a video'), the resource ('with a Gwanggo model'), and distinguishes from siblings like generate_image or get_credits by the generation context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for video generation but does not provide explicit guidance on when to use this tool over alternatives (e.g., generate_image) or mention prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_creditsA
Get the connected Gwanggo account email and remaining credit balance.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
A4.1/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It clearly states it retrieves email and credit balance, which implies a read-only operation. However, it does not explicitly state that no side effects occur or mention any authentication requirements, but for a simple get operation, the transparency is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is front-loaded and efficiently conveys the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description must explain return values. It mentions 'email and remaining credit balance,' which is adequate but could be more specific (e.g., data types, format). Given the simplicity, it meets the minimum viable standard.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and schema coverage is 100% (trivially). The description does not need to add parameter details. Baseline for zero parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the connected Gwanggo account email and remaining credit balance. This is a specific verb ('Get') and resource ('connected Gwanggo account email and remaining credit balance'), and it distinguishes from sibling tools which are about generation, tasks, and models.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking account info and credits before generating, but does not explicitly state when to use this tool versus alternatives. No when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_taskA
Check the status/result of a previous generation by its id.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Generation id returned by generate_image/generate_video |
TDQS
A3.7/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It states 'check' (read operation) but doesn't disclose idempotency, non-destructiveness, or potential errors. Minimal transparency beyond basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key information, no redundant words. Highly efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so description should compensate. It mentions 'status/result' but doesn't detail return value structure or possible statuses. Adequate but not complete for a check tool with no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and schema already describes the 'id' parameter clearly. Description adds no additional meaning beyond what schema provides, so baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'check', resource 'status/result of previous generation', and method 'by its id'. It effectively distinguishes from sibling tools like generate_image/generate_video (creation) and get_credits/list_models (different resources).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage after generation but lacks explicit guidance on when to use this tool versus alternatives. No exclusions or prerequisites mentioned, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Filter by model type |
TDQS
A3.9/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description discloses that it returns credit costs and per-model options. Does not mention any side effects, rate limits, or authentication needs, which is acceptable for a read-only list operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, efficient and front-loaded with verb and resource. No redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Describes output contents (credit costs, per-model options like aspect ratios, resolutions, durations) but does not detail output structure (e.g., slugs returned). Given no output schema, more detail would help.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema provides full coverage (100%) with description for the one parameter. The tool description adds context about what information is returned but does not significantly enhance parameter meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it lists available AI image/video generation models with credit costs and options. Distinguishes from siblings (generate_image, generate_video, get_credits) as a listing tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Call this first to pick a model slug', indicating it should be used before generation tools. Implicitly distinguishes from get_credits and task retrieval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
5 tool updates
v0.1.0- First observed
generate_image - First observed
generate_video - First observed
get_credits - First observed
get_task - First observed
list_models
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
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Generate images, video, music, voice and 3D through one API. 30 tools, 200+ models.
Best Image and video generation: 20+ models (Kling, Seedance, Veo, NB, FLUX.2), OAuth, pay-per-use.
Image, video, music and text generation across 100+ models through one endpoint.
Generate images, video, and audio with Glif's media-generation agent
Related MCP Servers
vicsee-mcp-serverofficial
AlicenseAqualityBmaintenanceEnables AI agents to generate, edit, and upscale videos and images using VicSee's API, with support for multiple models and asynchronous task polling.743 npmMIT- AlicenseAqualityCmaintenanceEnables 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.4MIT
- AlicenseAqualityCmaintenanceEnables AI agents to generate images and videos via the Corent API with automatic model routing, provider fallback, and tools for planning, creation, and balance management.764 npmMIT