# OCR-MCP

> Use this tool when you need to extract text from images or scanned documents with high accuracy, supporting various formats and layouts. It solves problems such as document digitization, data entry automation, and text recognition in multiple formats. The OCR-MCP tool takes in image files and outputs extracted text in various formats, preserving the original layout.

Canonical page: https://skillsregistry.net/skills/sandraschi-ocr-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sandraschi-ocr-mcp

## Description

Provides advanced OCR capabilities with multiple state-of-the-art backends (DeepSeek-OCR, Florence-2, DOTS.OCR, PP-OCRv5), supporting document processing, scanner integration, and multi-format output with layout preservation.

## Trust

- **Trust score (0–1):** 0.11
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pikfr6vsoa)
- **Repository:** <https://github.com/sandraschi/ocr-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": "sandraschi-ocr-mcp"
    }
  }
}
```

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