Zhenzhen Image 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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_model_guideA | 免费本地模型选择建议和配置状态；只检查密钥是否存在，不显示密钥、不请求云端。 |
| generate_imageA | 同步生成并落盘。默认逆向五参数；官转须显式 group=official。收费，POST 不自动重试。 |
| edit_imageA | 同步图像编辑并落盘；多图以 image[] 上传。高编辑精度场景建议 Sunburst。收费。 |
| submit_image_generationA | POST generations?async=true 提交收费异步绘图，立即返回 task_id。必须继续查询才能自动落盘。 |
| submit_image_editA | POST edits?async=true 提交收费异步编辑，以 image[] 上传；返回 task_id，之后查询并落盘。 |
| submit_image_batchA | 一次并发提交1–10项收费异步生成/编辑，默认并发3。收到任务编号即返回，不等待成图。同一(checkpointer,thread_id,task_id)及参数复用记录，参数冲突在提交前拒绝；不确定提交永不自动重发。 |
| get_image_batchA | 免费读取本地持久化检查点，恢复该会话所有 task_id/provider_task_id/最后观察状态；不查询供应商、不提交、不等待成图。 |
| get_batch_image_taskA | 按原(checkpointer,thread_id,task_id)查询供应商异步结果并自动落盘；只读HTTP有限重试。没有供应商编号时返回本地状态，不重新提交。云端失败为工具错误；检查 result.save_status。 |
| get_image_taskA | 查询 NOT_START（排队）/IN_PROGRESS/FAILURE/SUCCESS；暂时性查询故障最多尝试3次。save=true 时成功图片自动落盘；false 仅查询。不重新提交。 |
| wait_image_taskB | 有界轮询，NOT_START 排队和 IN_PROGRESS 处理中继续等待，成功后落盘；只读查询有限重试计入等待时限。超时返回 task_id/wait_timed_out，云端任务继续；可稍后再次查询。 |
| download_imageA | 按图片 URL 下载并校验 PNG/JPEG/WebP，自动落盘返回绝对路径；不会附带供应商 API Key。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| image_workflow | 根据用户需求选择模型与同步/异步绘图流程；模板本身不收费。 |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| model_resource | Static model advice and compatibility statement; no secrets or cloud calls. |
TDQS
Scored across 11 tools
The set contains four closely-related task-retrieval tools (get_image_task, get_batch_image_task, get_image_batch, wait_image_task) whose boundaries are only clear after reading full descriptions, risking misselection. The sync/async pairs (generate_image vs submit_image_generation, edit_image vs submit_image_edit) are conceptually the same operation split by mode, further muddying the choice.
Nearly all tools follow a verb_noun snake_case pattern (get_, submit_, wait_, download_, generate_, edit_). Minor deviations exist in noun composition (image_task vs batch_image_task vs image_batch) and in generate_image vs submit_image_generation, but the convention is largely readable and predictable.
11 tools is within the well-scoped range for an image generation/editing service covering sync, async, batch, query, and download. Slightly heavy because four of them overlap on task-status retrieval.
The surface covers the full lifecycle: sync/async generate and edit, batch submission, task querying/waiting, local checkpoint recovery, download, and model guidance. Minor gaps like explicit task cancellation or deletion are absent but not blocking.