labnana-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LABNANA_API_KEY | Yes | Labnana API key. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_subscriptionA | 获取当前 API Key 账户的订阅状态、可用积分（月度/永久/限时）、免费额度（freeUsages）与重置时间。对应 GET /openapi/v1/user/subscription。 |
| estimate_creditsA | 根据 provider、模型、尺寸、宽高比等参数预估生成图片所需的积分。同步返回，不实际生成图片、不扣除积分。对应 POST /openapi/v1/images/generation/estimate-credits。 |
| generate_imageA | 同步生成图片，直接返回 base64 图片数据与生成元数据。支持 Gemini 系列、GPT-Image-2、Wan2.7、Seedream 5.0 Pro。可传参考图片（fileUri 或 base64 inlineData）做图生图、改图。对应 POST /openapi/v1/images/generation。注意：同步接口返回体积大，4K 图片建议改用 generate_image_async。 |
| generate_image_asyncA | 创建图片生成任务并立即返回 taskId，不阻塞等待。任务成功后图片为公开链接，可用 get_generation_task 查询详情，或用 wait_for_generation_task 等待完成。适合大图、批量生成。对应 POST /openapi/v1/images/generation/async。 |
| list_generation_tasksA | 按创建时间倒序返回当前 API Key 用户的图片生成任务列表。对应 GET /openapi/v1/images/generation/tasks。 |
| get_generation_taskA | 查询图片生成任务状态。任务成功后 images 字段为公开图片链接数组，可直接下载。对应 GET /openapi/v1/images/generation/tasks/{taskId}。 |
| wait_for_generation_taskA | 轮询等待异步生成任务完成（success / fail），返回公开图片链接或失败原因。适合在 generate_image_async 之后直接调用，避免手动多次轮询。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clear, distinct purpose: subscription info, credit estimation, sync generation, async generation initiation, task listing, task status query, and task waiting. Even generate_image vs generate_image_async are cleanly separated by sync/async semantics.
Tool names mostly follow a consistent verb_noun (or verb_noun_modifier) pattern in snake_case, e.g., get_subscription, generate_image, list_generation_tasks. The only minor deviation is wait_for_generation_task which uses a phrasal verb, but it is still readable and predictable.
Seven tools is well-scoped for an image generation API with account/credit management. The set covers both synchronous and asynchronous flows, estimation, and task tracking without unnecessary bloat.
The core image generation workflow is complete: estimate credits, generate (sync/async), list, query, and wait for tasks. Minor gaps include lack of a cancel-task operation and no explicit tool to retrieve generated images directly, but these are workarounds via task links.