vision-mcp
Enables text-only models to perceive images via a vision-language model, supporting image analysis with simple descriptions or structured JSON for technical diagrams.
README
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
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。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.