# image-recognition-mcp

> Use this tool when you need to enable vision-less LLMs to recognize images, as it proxies clipboard screenshots and images to an OpenAI-compatible vision model, solving problems of image understanding and analysis. It takes image inputs and returns recognition outputs, providing a crucial interface for vision-based tasks. Ideal for use cases where text-based LLMs require visual context and understanding.

Canonical page: https://skillsregistry.net/skills/llt22-image-recognition-mcp  
JSON: https://api.skillsregistry.net/v1/skills/llt22-image-recognition-mcp

## Description

Gives vision-less LLMs the ability to recognize clipboard screenshots and images by proxying to an OpenAI-compatible vision model.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/tq5pgcsfur)
- **Repository:** <https://github.com/llt22/image-recognition-mcp>

## 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": "llt22-image-recognition-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/llt22-image-recognition-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/llt22-image-recognition-mcp/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