vision-mcp
# vision
纯文本模型看见图。复制截图即可。MIT。
安装用 npm，之后所有操作都是 `vision xxxxx`。需要 Node 22+。
## 从 GitHub 安装
```powershell
npm i -g github:hal666/vision-mcp
vision install
```
`vision install` 会接到本机已有的 Grok / Codex / Command Code / omp·Pi / Claude / Cursor / OpenCode。
DeepSeek Harness 额外一条（本机源码把路径换成仓库根目录）：
```powershell
dsh plugin --profile web add github:hal666/vision-mcp
```
插件会拦截聊天框附图：先用 vision backend 看图，再把描述交给 `deepseek-v4-flash` 这类纯文本模型。只装 MCP / Skill 不够，Harness 会在进模型前按 registry 拒图。
然后**重启 agent**。聊天输入框用斜杠指令（不是终端）：
```
/vision add <model> <apikey>
/vision delete <name>
/vision switch <name>
/vision enable
/vision disable
/vision status
/vision see
```
终端里同样的子命令不带 `/`：`vision add ...`。
## 指令（终端）
```
vision add <model> <apikey>
vision delete <name>
vision switch <name>
vision enable
vision disable
vision status
vision see
vision doctor
```
配置：`~/.vision-mcp/config.json`。密钥不进 mcp.json。
TDQS
Scored across 2 tools
The two tools have completely separate purposes: 'vision_see' performs the core image analysis and description, while 'vision_status' checks configuration and clipboard state. There is no overlap or ambiguity in their roles.
Both tools follow a consistent 'vision_verb' naming pattern: 'vision_see' and 'vision_status'. The prefix establishes the domain clearly, and the verbs are distinct and descriptive.
With only 2 tools, the server is on the borderline of being too thin for a typical MCP server. While the two tools cover the essential workflow, the set feels minimal and lacks ancillary tools that might be expected (e.g., configuration or image management).
The server covers the core use case of analyzing an image and checking readiness. Minor gaps exist (e.g., no explicit error recovery or format listing), but agents can work around these by combining the existing tools or relying on user assistance.