# eyes-mcp

> eyes-mcp — jamesbbbriz-eyes-mcp. Use this tool when you need to analyze visual data with text-only LLMs, as it provides local vision capabilities through a visual language model (VLM) and optical character recognition (OCR). It solves problems such as extracting text from images and screenshots, enabling agents to interface with visual interfaces. Inputs include screenshots and images, with outputs being extracted text for further analysis.

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

## Description

Gives text-only LLMs local vision by providing a local VLM and OCR via MCP, enabling agents to analyze screenshots and extract text from images.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/iwzkr7q5lt)
- **Repository:** <https://github.com/JamesbbBriz/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": "jamesbbbriz-eyes-mcp"
    }
  }
}
```

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