# mcp-vision

> Use this tool when you need to detect and analyze objects in images with zero-shot learning capabilities. The mcp-vision server takes image inputs and outputs object detection results, enabling Large Language Models (LLMs) to understand visual data. Ideal for applications requiring computer vision integration with LLMs, such as image analysis and object recognition tasks.

Canonical page: https://skillsregistry.net/skills/groundlight-mcp-vision  
JSON: https://api.skillsregistry.net/v1/skills/groundlight-mcp-vision

## Description

An MCP server that exposes HuggingFace computer vision models for zero-shot object detection, enabling LLMs to detect and analyze objects in images.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ym8easijam)
- **Repository:** <https://github.com/groundlight/mcp-vision>

## 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": "groundlight-mcp-vision"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/groundlight-mcp-vision` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/groundlight-mcp-vision/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