# local_vision

> Use this tool when you need to convert visual images into descriptive text for models lacking visual capabilities. It solves the problem of enabling large models to understand and process image data without requiring visual processing capabilities. The local_vision tool takes images as input and outputs descriptive text, making it ideal for applications where visual data needs to be translated into a text-based format.

Canonical page: https://skillsregistry.net/skills/davideasden-local-vision  
JSON: https://api.skillsregistry.net/v1/skills/davideasden-local-vision

## Description

An MCP that uses local VLM to convert images into descriptive text for large models without visual capabilities

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/DavidEasden/local_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": "davideasden-local-vision"
    }
  }
}
```

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