# mcp-local-vision

> mcp-local-vision — jshsakura-mcp-local-vision. Use this tool when you need to analyze visual data with a text-only LLM, enabling it to read and understand images and PDFs by leveraging a local vision model running on your GPU. This solves problems such as image classification, object detection, and document parsing, allowing for more comprehensive and accurate analysis. It takes images and PDFs as input and outputs text-based descriptions or classifications, ideal for use cases where visual data needs to be integrated with text-based AI models.

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

## Description

Lets a text-only LLM read images and PDFs by delegating to a vision model running on your own GPU.

## Trust

- **Trust score (0–1):** 0.68
- **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/smnz39kk4x)
- **Repository:** <https://github.com/jshsakura/mcp-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": "jshsakura-mcp-local-vision"
    }
  }
}
```

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