A
licenseNot graded
qualityD
maintenanceEnables text-only LLMs to analyze images by routing them to an OpenAI-compatible vision backend, supporting local files, URLs, and data URLs.
10 npm
MIT
vision-mcp
by Bbsong123
Click on "Deploy 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-mcpAnalyze the circuit diagram in circuit.png and summarize its function."
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.
Multimodal Perception（视觉感知 MCP + Codex Skill）
让 Codex 背后的文本模型拥有"视觉感知能力"：视觉模型作为视觉专家提供观察报告， 主文本模型结合视觉结果完成最终分析、推理和决策。
架构
用户 → Codex + 主文本模型
→ 判断当前推理是否需要视觉信息
→ 需要时调用 analyze_image(image, question) MCP
→ 视觉专家返回观察报告（文本或 JSON）
→ 主模型结合视觉结果继续推理Related MCP server: Image-Vision MCP Server
文件结构
vision-mcp/
├── server.py # FastMCP 入口与 analyze_image(image, question)
├── model_client.py # 单一 OpenAI-compatible 视觉模型客户端
├── config.py # 配置加载（环境变量 / .env）
├── requirements.txt
└── README.md配置
复制 .env.example 为 .env 并填写视觉模型 API Key：
QWEN_API_KEY=sk-...默认使用 Qwen3-VL（qwen3-vl-flash）。可通过环境变量覆盖端点与模型：
VISION_BASE_URL、VISION_MODEL、VISION_PROVIDER、VISION_TIMEOUT 等。
MCP 工具
analyze_image(
image: str, # 本地路径 / http(s) URL / base64 / data URI / PDF
question: str # 主模型希望从图中了解什么
)简单问题（如"这是什么"）→ 返回简洁文本描述。
结构/技术分析（控制框图、电路、图表、工程图等）→ 返回 JSON 视觉报告：
observation/key_elements/preliminary_analysis/possible_issues/uncertainty。
Skill
skills/multimodal-perception/SKILL.md：告诉主模型"你不是纯文本 Agent，
任务依赖视觉信息时调用视觉能力，不要猜测；视觉报告只提供观察与初步判断，
最终推理由主模型完成"。
Codex Desktop 挂载
[mcp_servers.multimodal_router]
command = 'E:\csprogram\vision-mcp\.venv\Scripts\python.exe'
args = [ 'E:\csprogram\vision-mcp\server.py' ]
startup_timeout_sec = 30
[mcp_servers.multimodal_router.env]
PYTHONUTF8 = '1'
PYTHONIOENCODING = 'utf-8'修改配置或代码后需重启 Codex Desktop，并新建会话生效。
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Give agents eyes on any web page: structured context, and changes explained in plain language.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables text-only language models to 'see' and describe images by calling multimodal APIs (OpenAI, Anthropic) for image analysis.-
- FlicenseNot gradedqualityCmaintenanceEnables text-only LLMs to process images by describing them through a configurable vision model.-
- AlicenseNot gradedqualityBmaintenanceEnables text-only LLMs to understand images by converting them into text descriptions, supporting multiple vision backends like cloud APIs, local models, and OCR engines.1MIT