ai-media-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_model_capabilitiesA | 查询各模型支持的图片/视频分辨率、宽高比、时长等能力清单（纯本地查询，不调用 API、不收费）。可指定 model 精确查询某模型，或传 aspect_ratio/size/resolution 反查可用模型。 |
| probe_capabilitiesA | 实测各模型当前支持的分辨率/宽高比（真实调用试探，会消耗少量生成配额，默认只试探少量组合）。结果写入本地缓存，list_model_capabilities 自动合并。可选 model 只探测指定模型。 |
| generate_imageA | 生成/编辑图片（OpenAI 兼容 /images/generations，模型名透传：gpt-image-2、gemini-3-pro-image、grok-imagine-image-quality、即梦、doubao-seedream 等）。默认保存到本地并只返回文件路径（零 base64）。 |
| generate_videoA | 提交视频生成任务（不等待）。grok-imagine-video* 走 /videos/generations；即梦 as-sd2.0-fast / video-ds-2.0* 走 /videos。自动按模型名路由。 |
| get_video_statusA | 查询视频任务状态（自动兼容即梦 /videos/{id} 与 grok /videos/{id} 两种路由）。 |
| generate_video_and_waitA | 提交视频任务、轮询到完成并下载到本地，返回本地文件路径（零 base64）。可能需要数分钟。 |
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 6 tools
Each tool has a clearly distinct purpose: local capability lookup vs. live probing, image generation vs. video generation, async submission vs. status polling vs. synchronous wait-and-download. Even related pairs like generate_video and generate_video_and_wait are cleanly separated by behavior.
All tool names follow a consistent verb_noun snake_case pattern: list_, probe_, generate_, get_. The longer generate_video_and_wait is still a predictable extension of generate_video without mixing conventions.
With six tools, the server is well-scoped for an AI media generation service. Each tool addresses a distinct part of the workflow: capability discovery, image generation, video submission, status polling, and synchronous video generation.
The surface covers the core workflow: check capabilities, generate an image, submit/synchronously wait for video, and poll video status. Minor gaps exist, such as no way to cancel a pending video job or list/manage previously generated files, but these are not critical to the server's stated purpose.