# PaddleOCR

> Use this tool when you need to extract text from images, enabling AI agents to access and process visual data. PaddleOCR solves problems such as digitizing handwritten or printed texts, and automating data entry from images, by taking image files as input and outputting extracted text. It is ideal for use cases where local text recognition is required, providing a secure and efficient solution for text extraction.

Canonical page: https://skillsregistry.net/skills/yuanjinke-paddleocr-mcp  
JSON: https://api.skillsregistry.net/v1/skills/yuanjinke-paddleocr-mcp

## Description

A local OCR server using PaddleOCR that enables AI agents to extract text from images.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qby60772ms)
- **Repository:** <https://github.com/YuanJinke/paddleocr_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": "yuanjinke-paddleocr-mcp"
    }
  }
}
```

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