# Computer Vision Tools

> Use this tool when you need to enable AI assistants to perform complex visual tasks, such as generating images from text prompts, extracting text from images, and identifying objects in photos. It solves problems like image understanding, text extraction, and object detection, providing a suite of computer vision capabilities through APIs and containerized components. The tool accepts text prompts and image inputs, and outputs generated images, extracted text, and object detections, making it ideal for use cases that require seamless visual processing within conversation interfaces.

Canonical page: https://skillsregistry.net/skills/omidsrezai-cv-tools  
JSON: https://api.skillsregistry.net/v1/skills/omidsrezai-cv-tools

## Description

CV-MCP-Tools provides a suite of computer vision capabilities for language models through the Model Context Protocol. The repository includes three main components: an image generation server using FLUX.1-Schnell, an OCR server leveraging Qwen-VL and Janus models for text extraction and image understanding, and an object detection tool built on YOLO. Each component is containerized with Docker for easy deployment and exposes APIs for seamless integration. The implementation supports both Claude Desktop and Ollama through configuration files, with MinIO integration for image storage and retrieval. This toolset enables AI assistants to perform complex visual tasks including generating images from text prompts, extracting text from images, and identifying objects in photos without leaving the conversation interface.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/omidsrezai-cv-tools)
- **Repository:** <https://github.com/omidsrezai/cv-mcp-tools>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "omidsrezai-cv-tools"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/omidsrezai-cv-tools` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/omidsrezai-cv-tools/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt