Vision MCP for Reasonix
The Vision MCP for Reasonix server adds visual understanding to text-only models (e.g., DeepSeek V4) via these tools:
analyze_image: Describe or answer questions about an image using natural language. Supports local files or URLs, with detail level (low/high/auto).
ocr_image: Extract text from images via OCR. Output as plain text, Markdown, or JSON; supports language hints (e.g., 'zh,en').
compare_images: Compare 2–4 images side-by-side to identify differences and similarities. Accepts local files or URLs.
analyze_video: Analyze video content (needs a video-capable model like Qwen3-VL).
Inputs: local file paths (auto-converted to base64) or URLs. Supports JPEG, PNG, GIF, WebP, BMP, SVG for images; MP4, AVI, MOV, MKV, WebM for videos.
Provides tools for image and video analysis using OpenAI-compatible vision models, enabling tasks like analyzing images, OCR, comparing images, and video content analysis.
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., "@Vision MCP for ReasonixAnalyze this screenshot for UI issues"
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.
👁️ Vision MCP for DS
给 DeepSeek V4 等纯文本模型补上视觉。
DS V4 推理强,但看不到图。本项目是一个 MCP Server,把视觉模型的图像/视频理解能力,作为工具暴露给任何 MCP 客户端 —— Reasonix、ZCode,一份代码多处通用。截图分析、UI 对比、OCR、视频解读,各司其职。
⚠️ 客户端兼容性:经测试,Reasonix / ZCode 可正常调用。WorkBuddy 存在工具触发不稳定的问题(其「图片输入」开关与 MCP 工具路由冲突),暂未列入支持,正在
workbuddy-compat分支研究中。
基于 Loveacup/vision-mcp-server(MIT)改造,感谢原作者。
工作原理 · 快速开始 · 部署到其它电脑 · Profile 预设 · 工具
💡 工作原理
┌─────────────────────────────┐ MCP/stdio ┌──────────────────────┐ HTTPS/Bearer ┌─────────────────────┐
│ Reasonix / ZCode │ ◄────────► │ Vision MCP for DS │ ─────────────► │ 视觉模型 (MiMo 等) │
│ (DS V4,纯文本) │ │ (本机 node 进程) │ │ opencode.ai/zen/go │
└─────────────────────────────┘ └──────────────────────┘ └─────────────────────┘
│
▼
┌──────────────┐
│ 本地文件系统 │ (图片/视频 → base64)
└──────────────┘DS V4 负责代码推理与任务编排。
遇到截图/UI/图片时,客户端自动调用
visionMCP 的工具,由视觉模型提供理解。本地文件会被自动转成 base64 data URI,对客户端完全透明。
Related MCP server: Vision MCP Server
🚀 快速开始
1. 安装
git clone https://github.com/Dellety/vision-mcp-for-ds.git
cd vision-mcp-for-ds
npm install && npm run build2. 配置
创建 .env(最简:选 profile + 填 key):
VISION_PROFILE=opencode # OpenCode Go 套餐,一个 key 接入多家模型
VISION_API_KEY=你的key # https://opencode.ai/go 订阅后获取API Key 只走环境变量,不要写入任何提交到仓库的文件。
profile | 供应商 | 默认模型 |
| OpenCode Go 套餐 |
|
| 智谱 BigModel |
|
| OpenAI |
|
| 阿里通义千问 VL |
|
| 本地模型 |
|
换模型不换供应商:加 VISION_MODEL=glm-5.2。
完全换端点:加 VISION_BASE_URL=...,或直接换 VISION_PROFILE。
3. 接入客户端
三个客户端的 MCP 配置格式各不相同,按你用的客户端选一个。下面 /ABSOLUTE/PATH/TO 替换为实际部署路径(如 ~/vision-mcp-for-ds)。
[[plugins]]
name = "vision"
type = "stdio"
command = "node"
args = ["/ABSOLUTE/PATH/TO/vision-mcp-for-ds/dist/index.js"]
env = { VISION_PROFILE = "opencode", VISION_API_KEY = "你的key" }还需在 ~/.reasonix/mcp-activation.json 里启用该 server(首次添加后 Reasonix 一般会自动写入):
{
"version": 1,
"overrides": [
{ "scope": "global", "source": "user_config", "server": "vision", "enabled": true }
]
}在 mcp.servers 下添加(server 名可自定义):
"ds-vision": {
"type": "stdio",
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/vision-mcp-for-ds/dist/index.js"],
"env": {
"VISION_PROFILE": "opencode",
"VISION_API_KEY": "你的key"
},
"timeoutMs": 20000
}💡 首选方案:OpenCode 在插件市场推荐了社区视觉插件
opencode-see-image(在opencode.jsonc的plugin字段添加即可),开箱即用。本方案对 OpenCode 只是备选——当你想用自己的视觉模型/key、或需要 OCR/视频/对比等插件不具备的工具时,再配我们的 server。
⚠️ OpenCode 的 mcp 配置不允许写入 API key 等资产信息。key 通过部署目录的
config.json传入(见下方第 2 步)。
第 1 步:在 opencode.jsonc 的 mcp 字段里添加(用 cwd 指向部署目录,让 server 能读到 config.json):
"vision": {
"type": "local",
"command": ["node", "/ABSOLUTE/PATH/TO/vision-mcp-for-ds/dist/index.js"],
"cwd": "/ABSOLUTE/PATH/TO/vision-mcp-for-ds",
"enabled": true,
"timeout": 10000
// 不写 environment —— key 走 config.json
}第 2 步:在部署目录创建 config.json(从 config.example.json 复制后填 key):
cd /ABSOLUTE/PATH/TO/vision-mcp-for-ds
cp config.example.json config.json
# 编辑 config.json,填入 apiKey{
"profile": "opencode",
"apiKey": "你的key"
}标准 MCP stdio 配置,key 走 env:
{
"mcpServers": {
"vision": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/vision-mcp-for-ds/dist/index.js"],
"env": {
"VISION_PROFILE": "opencode",
"VISION_API_KEY": "你的key"
}
}
}
}启动客户端,让 DS V4 分析一张本地图片即可验证。启动日志应为:
Vision MCP for DS started (profile: opencode, model: mimo-v2.5, ...)
📦 部署到其它电脑
面向「目标机可直连公网」的场景,提供 tar 包一键部署(不发布 npm)。
源机打包:
npm run pack
# → dist/vision-mcp-for-ds-deploy-v1.3.0.tar.gz目标机安装:
tar xzf vision-mcp-for-ds-deploy-v1.3.0.tar.gz -C ~
cd ~/vision-mcp-for-ds
npm ci --omit=dev # 只装 2 个生产依赖(sdk + zod),秒级完成
./scripts/health-check.sh # 自检:node 版本 / 依赖 / key / 端点可达然后按上面「接入客户端」的对应章节配置你用的客户端。OpenCode 用户注意:还需在部署目录 cp config.example.json config.json 并填 key(OpenCode 不允许在 mcp 配置里写资产信息)。
生产依赖仅
@modelcontextprotocol/sdk+zod,纯 JS 无 native binding,跨平台安全。
🎯 Profile 预设
一个 profile 自带正确端点和默认模型,部署时只需选 profile + 填 key。配置优先级:
1. 显式环境变量 (VISION_BASE_URL / VISION_MODEL / ...)
2. config.json 中的显式字段
3. VISION_PROFILE 指向的预设(填充未指定的字段)
4. 兜底:profile=opencode变量 | 默认 | 说明 |
|
| 预设供应商,见上表 |
| (见 profile) | OpenAI 兼容端点(覆盖 profile) |
| (见 profile) | 模型名(覆盖 profile) |
| (空) | API key,只走环境变量 |
|
| 最大响应 tokens |
|
| 采样温度 |
🛠️ 工具
工具 | 说明 | 关键参数 |
🔍 | 自然语言分析图像 |
|
📝 | OCR 文字识别 |
|
🔀 | 对比 2–4 张图像 |
|
🎬 | 视频内容分析(需视频模型) |
|
支持格式: JPEG/PNG/GIF/WebP/BMP/SVG | MP4/AVI/MOV/MKV/WebM 输入: 本地路径(自动转 base64)或 URL
📁 项目结构
vision-mcp-for-ds/
├── src/
│ ├── index.ts # MCP server 入口 + 工具注册
│ ├── config.ts # 配置加载(env > config.json > profile)
│ ├── types.ts # 类型定义
│ ├── tools/ # 4 个视觉工具
│ └── utils/ # API 客户端 + 文件处理
├── scripts/
│ ├── pack.sh # 打包部署 tar
│ ├── health-check.sh # 部署自检
│ └── verify-config.sh # 配置解析验证
└── docs/superpowers/specs/ # 设计文档📄 License
本项目基于 Loveacup/vision-mcp-server(MIT)改造,特此致谢原作者。
在原项目基础上增加了 Profile 多预设、多客户端通用化、安全重试与超时保护,并重命名为 vision-mcp-for-ds。
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 Servers
- AlicenseAqualityDmaintenanceEnables image analysis and understanding using Vision Language Models through OpenAI-compatible APIs. Supports analyzing images from URLs or local files with custom prompts.Last updated13MIT
- AlicenseBqualityDmaintenanceEnables vision capabilities for any AI model by routing image analysis requests through OpenRouter's vision models. It provides tools to analyze images from URLs, local file paths, or base64 data.Last updated213020MIT
- AlicenseAqualityDmaintenanceEnables AI agents to analyze images, extract text, compare images, and analyze video through any OpenAI-compatible vision model.Last updated45715MIT
- Flicense-qualityCmaintenanceEnables image recognition using vision models via OpenAI-compatible APIs, supporting multiple platforms like OpenAI, DeepSeek, and Ollama.Last updated
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Generate, edit and upscale AI video and images from any agent via VicSee.
Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Dellety/vision-mcp-for-ds'
If you have feedback or need assistance with the MCP directory API, please join our Discord server