# ocr-api

> ocr-api — ia-generative-ocr-api. Use this tool when you need to extract text from images or PDF files, solving problems such as document digitization and text recognition. The ocr-api takes image or PDF files as input and outputs extracted text, providing a simple interface for optical character recognition tasks. Ideal for use cases where manual text entry is impractical, such as large-scale document processing or automated data entry.

Canonical page: https://skillsregistry.net/skills/ia-generative-ocr-api  
JSON: https://api.skillsregistry.net/v1/skills/ia-generative-ocr-api

## Description

Get OCR from pdf and images

## Trust

- **Trust score (0–1):** 0.51
- **Verification tier:** scanned
- **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/IA-Generative/ocr-api)

## 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": "ia-generative-ocr-api"
    }
  }
}
```

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