# agent-eyes-mcp

> agent-eyes-mcp — huangzhixin0420-agent-eyes-mcp. Use this tool when you need to enable text-only LLM agents to understand visual content by converting images into descriptive text. It solves problems of visual awareness and context understanding for AI models, allowing them to process and respond to image-based inputs. The tool takes image inputs and outputs descriptive text via MCP or CLI interfaces.

Canonical page: https://skillsregistry.net/skills/huangzhixin0420-agent-eyes-mcp  
JSON: https://api.skillsregistry.net/v1/skills/huangzhixin0420-agent-eyes-mcp

## Description

Give text-only LLM agents eyes by describing images through a vision-language model via MCP or CLI.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qd7xvc5ak4)
- **Repository:** <https://github.com/huangzhixin0420/agent-eyes-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": "huangzhixin0420-agent-eyes-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/huangzhixin0420-agent-eyes-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/huangzhixin0420-agent-eyes-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