cv-mcp-tools
A repository showcasing integration of specialized computer vision tools with language models through MCP.
Documentation
CV MCP Tools
A collection of Model Context Protocol (MCP) servers and services that integrate specialized computer vision capabilities with language models. This repository demonstrates how to build modular CV tools that can be easily composed and orchestrated through MCP.
🔧 Components
MCP Servers
- **Object Detection MCP** - YOLO-based object detection with MinIO integration
- **OCR + Image Generation MCP** - Combined OCR and image generation with iterative validation workflows
Standalone Services
- **Image Generator Server** - FLUX.1-schnell diffusion model service
- **OCR Server** - Multi-model OCR service (Qwen-VL, Janus)
🚀 Quick Start
Prerequisites
- Python 3.11+
- UV package manager
- Docker with GPU support
- MinIO server (for MCP servers)
Running MCP Servers
# Object Detection
cd object_detection_mcp
uv run object_detector.py
# OCR + Image Generation
cd ocr_imagen_mcp
uv run ocr_imagen.pyRunning Standalone Services
# Image Generator
docker buildx build -t flux-schnell -f image_generator_server/Dockerfile .
docker run --gpus all -p 6070:6070 flux-schnell
# OCR Server
docker buildx build -t ocr-server -f ocr_server/Dockerfile .
docker run --gpus all -p 6080:6080 -p 6081:6081 ocr-server🔗 Integration with Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"object_detection": {
"command": "uv",
"args": ["--directory", "/path/to/object_detection_mcp", "run", "object_detector.py"],
"env": {
"YOLO_MODEL_NAME": "yolo11m.pt",
"YOLO_CONF_THRESHOLD": "0.45",
"MINIO_URL": "localhost:9000",
"MINIO_ACCESS_KEY": "your-key",
"MINIO_SECRET_KEY": "your-secret"
}
}
}
}📁 Repository Structure
cv-mcp-tools/
├── object_detection_mcp/ # YOLO object detection MCP server
├── ocr_imagen_mcp/ # Combined OCR + image generation MCP
├── image_generator_server/ # Standalone FLUX image generation service
├── ocr_server/ # Standalone OCR service
└── CLAUDE.md # Development guide for Claude Code🎯 Use Cases
- Automated Content Analysis - Object detection and OCR for document processing
- Iterative Image Generation - Generate images with text validation loops
- Multi-Modal Workflows - Combine vision and language models for complex tasks
- Modular CV Pipeline - Mix and match components as needed
📖 Documentation
Each component has its own README with detailed setup instructions:
Frequently asked questions
What is cv-mcp-tools?
cv-mcp-tools is A repository showcasing integration of specialized computer vision tools with language models through MCP.
How do I install cv-mcp-tools?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is cv-mcp-tools open source?
Yes — it is hosted on GitHub at https://github.com/omidsrezai/cv-mcp-tools and has 1 stars.
Related MCP tools
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to
🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。 for the Model Context Protocol. Enhance AI assistants with po
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP