wan27-image-edit
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@wan27-image-editUse both reference images: put the hat from image 2 onto the person in image 1."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
wan27-image-edit
万相2.7 图像编辑(多图参考) 的 MCP 服务,封装阿里云百炼(华北2·北京)异步生图接口。
通过 uvx 从 GitHub 直接安装运行,可一键部署到阿里云函数计算(FC)「创建 MCP 服务」页面。
暴露的工具
wan27_image_edit — 传入 1–9 张参考图 + 文字指令,返回生成图像 URL(PNG,24 小时内有效)。
参数 | 说明 | 默认 |
| 文字编辑指令(≤5000 字符),如“把图2的涂鸦喷绘在图1的汽车上” | 必填 |
| 1–9 张图,数组顺序=图1/图2…;公网 URL 或 | 必填 |
|
|
|
|
|
|
| 生成张数 1–4 |
|
| 右下角是否加“AI生成”水印 |
|
| 随机种子 0–2147483647 | 可选 |
Related MCP server: Volcengine Image Generation MCP Server
环境变量
DASHSCOPE_API_KEY(必填):百炼 API Key。WAN_WORKSPACE_ID(可选):业务空间 ID,默认内置ws-bw8c2tma2afa2fsl,请求域名https://{id}.cn-beijing.maas.aliyuncs.com。
本地快速自测(可选)
# 需要 uv(pip install uv)
export DASHSCOPE_API_KEY=sk-xxxx
uvx --from /绝对路径/到/本仓库 wan27-image-edit
# 或用 MCP Inspector 连 STDIO 测试:
npx @modelcontextprotocol/inspector uvx --from . wan27-image-edit部署步骤
1. 推到 GitHub(公开仓库)
在 GitHub 新建一个公开仓库 wan27-image-edit,然后:
cd wan27-image-edit
git init
git add .
git commit -m "init wan2.7 image-edit MCP server"
git branch -M main
git remote add origin https://github.com/nanchenyi/wan27-image-edit.git
git push -u origin main代码里不含任何密钥,公开只是暴露这层薄封装源码。
2. 阿里云 FC「创建 MCP 服务」页面填写
服务名称:
wan27-image-edit安装方式:选
uvx部署方式:打开 极速模式(SSE 会话更稳;按 0.13 元/时计费)
部署地域:华北2(北京)
MCP 服务配置:粘贴下面 JSON,只把
DASHSCOPE_API_KEY换成你自己的真实 Key
{
"mcpServers": {
"wan27-image-edit": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/nanchenyi/wan27-image-edit.git",
"wan27-image-edit"
],
"env": {
"DASHSCOPE_API_KEY": "sk-你的真实Key",
"WAN_WORKSPACE_ID": "ws-bw8c2tma2afa2fsl"
}
}
}
}若页面提供「变量管理 / 服务变量(加密)」,更推荐把
DASHSCOPE_API_KEY作为加密变量托管,配置里用变量引用,避免明文出现在 JSON。
3. 保存后测试
页面「测试」入口选择 SSE / 对应传输类型,调用 wan27_image_edit:
传 prompt + 至少一张公网可访问的 images URL,确认返回图像链接。
常见问题
鉴权失败 / 跨地域报错:北京与新加坡的 API Key、域名不通用,确认 Key 与
cn-beijing域名同属北京地域。current user api does not support synchronous calls:本服务走的是异步接口(带X-DashScope-Async: enable),正常不会出现;若自行改造为同步路径需注意。图像 URL 打不开:链接仅 24 小时有效,请及时下载保存。
启动报
No module named 'mcp.server.fastmcp':依赖已锁定mcp>=1.2.0,<2。mcp 2.x 把FastMCP改名为MCPServer,不要放开这个上限。
Available Tools
1 toolwan27_image_editA
万相2.7 图像编辑(多图参考)。
参数: prompt: 文字指令,描述如何编辑/融合(≤5000 字符)。例如“把图2的涂鸦喷绘在图1的汽车上”。 images: 1-9 张参考图,按数组顺序定义“图1/图2...”。每项为公网可访问 URL 或 data:image/{jpeg|png|webp};base64,<...> 字符串。图像格式 JPEG/JPG/PNG(无透明)/BMP/WEBP, 宽高 [240,8000]px、宽高比 [1:8,8:1]、单张 ≤20MB。 model: wan2.7-image-pro(专业版)或 wan2.7-image(更快)。 size: 输出分辨率规格,1K / 2K / 4K。图像编辑场景 pro 与 image 最高均 2K;4K 仅文生图可用。 n: 生成张数,1-4。 watermark: 是否在右下角加“AI生成”水印,默认 False。 seed: 随机种子 [0,2147483647],相同 seed 结果相对稳定(可选)。
返回: 生成图像的 URL 列表(PNG,链接 24 小时内有效,请及时下载保存)。
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | ||
| seed | No | ||
| size | No | 2K | |
| model | No | wan2.7-image-pro | |
| images | Yes | ||
| prompt | Yes | ||
| watermark | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
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 discloses the output format (URLs, PNG), the 24-hour link expiry, the watermark default, and size constraints for the edit scenario. This gives the agent important behavior it could not infer from the schema, such as prompt length limits and aspect ratio constraints. It does not cover error cases or rate limits, but for a generation endpoint the disclosed behavior is valuable and sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is structured as a labeled parameter list with clear bullets. It opens with a meaningful one-line title before diving into parameters. Every sentence adds necessary information: no filler, no redundancies with the schema beyond what is needed for clarity. The list format makes it easy to scan.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Even though an output schema is present, the description goes further by explaining the return structure (URL list, PNG, expiry). It also covers all input constraints and defaults, making the tool usable without external documentation. For a tool with 7 parameters and no annotations, this description is complete in the context of the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must fully compensate, and it does. For every parameter (prompt, images, model, size, n, watermark, seed) it adds concrete semantics: prompt length, image count range, data URI format, accepted formats, dimension limits, aspect ratio, file size, model names, size options with the 4K restriction, n range, watermark behavior, and seed range. This is exemplary compensation for a schema that provides no field descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: it performs image editing with multi-image reference using the Wan 2.7 model. Even without sibling tools, the word 图像编辑 (image editing) plus the multi-reference detail makes the purpose unmistakable, and the rest of the description confirms the edit/merge behavior.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit usage guidance on when to choose each model (专业版 vs 更快) and warns that 4K is unavailable for image editing, available only for text-to-image. This is clear and useful for selecting parameters correctly. No sibling tools are listed, so no alternative-tool guidance can be expected, but the coverage within this tool's scope is strong.
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.
1 tool update
v0.1.0- First observed
wan27_image_edit
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between overlapping tools. The tool's purpose is clearly defined as image editing with multiple reference images.
With a single snake_case tool name, there is no inconsistent convention to penalize. However, there is not enough variety to fully confirm a naming pattern.
A single tool feels thin for an MCP server, even though it encapsulates a complete image-editing operation. The count is borderline but not extreme.
The tool covers the core image editing workflow with parameters for prompt, reference images, model, size, count, watermark, and seed. Minor gaps exist, such as no explicit output retrieval or model listing, but the essential use case is fully addressed.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Edit images over MCP with object removal, background removal, and guided generative edits.
Generate images, video, music, voice and 3D through one API. 30 tools, 200+ models.
Generate and edit images, videos, and audio with 150+ models from 20+ vendors.
Related MCP Servers
- AlicenseCqualityCmaintenanceEnables users to generate high-quality images using ModelScope's Qwen-Image model through natural language prompts. Supports async task processing with both image URL and base64 encoded data output options.12MIT
- FlicenseBqualityDmaintenanceEnables AI-powered text-to-image generation using Volcengine's API with support for multiple image sizes, customizable parameters like guidance scale and seed, and flexible output formats.1-
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered image generation using Volcano Engine's SeeDream 4.0 model. Supports custom sizes, reference images, and automatic prompt generation without complex prompting.14MIT
- FlicenseNot gradedqualityCmaintenanceEnables generating AI images using BytePlus Seedream models (4.5 and 5.0 Lite) via natural language, supporting text-to-image, reference-based editing, and sequential multi-panel sets.-