# yandex-vision-ocr-mcp

> Use this tool when you need to extract text from images and PDFs using Optical Character Recognition (OCR) technology. It solves problems such as digitizing printed documents, automating data entry, and enhancing document search capabilities. The tool takes images and PDFs as input and outputs recognized text in various formats, making it ideal for use cases where text extraction and document processing are required.

Canonical page: https://skillsregistry.net/skills/chupre-yandex-vision-ocr-mcp  
JSON: https://api.skillsregistry.net/v1/skills/chupre-yandex-vision-ocr-mcp

## Description

Provides OCR capabilities for images and PDFs using Yandex Vision API. Supports multiple recognition models and output formats.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **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/affjkrq4d0)
- **Repository:** <https://github.com/chupre/yandex-vision-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": "chupre-yandex-vision-ocr-mcp"
    }
  }
}
```

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