# optical-read-mcp

> optical-read-mcp — hyprcat-optical-read-mcp. Use this tool when you need to efficiently process large files for vision models, converting text into compact PNG images to reduce token usage. It solves the problem of excessive token consumption when dealing with lengthy files, enabling more cost-effective and streamlined processing. The optical-read-mcp tool takes file contents as input and outputs line-numbered PNG images, ideal for use cases where vision models require text data in image format.

Canonical page: https://skillsregistry.net/skills/hyprcat-optical-read-mcp  
JSON: https://api.skillsregistry.net/v1/skills/hyprcat-optical-read-mcp

## Description

MCP server that converts file contents into compact, line-numbered PNG images for vision models to read, reducing token usage by roughly 7x for large files.

## 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/ba3fuc5fdp)
- **Repository:** <https://github.com/hyprcat/optical-read-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": "hyprcat-optical-read-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hyprcat-optical-read-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hyprcat-optical-read-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