目录 / Imaginode
Imaginode
Generate AI images and videos from any MCP client, built by Frank Houbre, an AI expert based in France. 48 models share a single credit balance: Flux, Imagen 4, Seedream, Recraft and GPT Image for stills, Kling, Seedance, Veo 3.1 with audio, MiniMax, Wan and PixVerse for video. No account to open with each provider, no stack of subscriptions. **Four tools.** `list_models` returns the catalogue with the credit cost of every model, so the agent knows the price before it spends anything. `generate_image` creates an image and waits, returning the URL directly. `generate_video` starts a video and returns a request_id. `get_generation_status` follows a generation to its final URL. **Cost is never a surprise.** One credit is about $0.012, an image costs 1 to 7 credits and a video 26 to 60. A failed generation refunds its credits automatically. **Authentication.** Pass your key as the `apiKey` parameter, full value including the prefix: `Bearer imk_...`. Create one at https://imaginode.ai/profile. New accounts get trial credits without a card. The same models are also available on a node canvas at https://imaginode.ai, so a board an agent starts can be reopened and edited by hand.
接入信息
- 传输形态
- http
- 鉴权方式
- 需 API Key(需要配置:apiKey)
- 端点
https://imaginode--imaginode-ai.run.tools
{
"mcpServers": {
"Imaginode": {
"headers": {
"Authorization": "Bearer \u003cYOUR_KEY\u003e"
},
"url": "https://imaginode--imaginode-ai.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| list_models | List the available AI models with their kind (image, video), default cost in credits (1 credit = $0.012, or €0.01 when billed in euros) and billable options. Call this before generating if you need a specific model, otherwise sensible defaults are used. |
| generate_image | Generate an image from a text prompt (optionally with input images for editing or reference). Waits for the result and returns the image URL. Costs credits from the connected Imaginode account; failures are refunded. |
| generate_video | Start a video generation from a text prompt (optionally with a start image). Returns immediately with a request_id and the cost in credits: poll get_generation_status every 30 seconds until it completes (typically 1 to 5 minutes, up to 30 for long jobs). Failures are refunded. |
| get_generation_status | Check a generation started with generate_video (or a generate_image that timed out). Returns running, completed (with output URLs) or failed (refunded). |
提交举报 / 纠错
侵权举报经核验成立后,我们会即时下线该条目并删除已存的内容副本。