# squint-mcp

> squint-mcp — thejian-squint-mcp. Use this tool when you need to generate text-based representations of images for language models that don't have visual capabilities. Squint-mcp solves the problem of limited visual understanding in LLMs by creating imaginary descriptions of images, allowing for more inclusive and diverse text generation. It takes image prompts as input and outputs descriptive text, making it a useful interface for applications where visual data needs to be translated into textual format.

Canonical page: https://skillsregistry.net/skills/thejian-squint-mcp  
JSON: https://api.skillsregistry.net/v1/skills/thejian-squint-mcp

## Description

Most LLMs see images. With squint-mcp, the rest imagine seeing them.

## Trust

- **Trust score (0–1):** 0.81
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/theJian/squint-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": "thejian-squint-mcp"
    }
  }
}
```

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